Merge pull request #1122 from maxulysse/annotation_cache

FEAT: Use annotation-cache and update VEP to v110
nf-core · Aug 17, 2023 · 2934fcf · 2934fcf
2 parents 66af584 + 6ef8a46
commit 2934fcf
Show file tree

Hide file tree

Showing 13 changed files with 73 additions and 127 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#1158](https://github.com/nf-core/sarek/pull/1158) - Add preprint
 - [#1159](https://github.com/nf-core/sarek/pull/1159) - ISMB Poster
 - [#1173](https://github.com/nf-core/sarek/pull/1173) - CI tests for VQSR track with stub runs
+- [#1122](https://github.com/nf-core/sarek/pull/1122) - Add `annotation cache` functionality
 
 ### Changed
 

diff --git a/conf/igenomes.config b/conf/igenomes.config
@@ -37,11 +37,9 @@ params {
             mappability           = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/Control-FREEC/out100m2_hg19.gem"
             snpeff_db             = 87
             snpeff_genome         = 'GRCh37'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
-            vep_version           = '108.2'
         }
         'GATK.GRCh38' {
             ascat_alleles         = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/ASCAT/G1000_alleles_hg38.zip"
@@ -74,34 +72,28 @@ params {
             pon_tbi               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi"
             snpeff_db             = 105
             snpeff_genome         = 'GRCh38'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'GRCh38'
             vep_species           = 'homo_sapiens'
-            vep_version           = '108.2'
         }
         'Ensembl.GRCh37' {
             bwa                   = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
             readme                = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt"
             snpeff_db             = 87
             snpeff_genome         = 'GRCh37'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
-            vep_version           = '108.2'
         }
         'NCBI.GRCh38' {
             bwa                   = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
             snpeff_db             = 105
             snpeff_genome         = 'GRCh38'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'GRCh38'
             vep_species           = 'homo_sapiens'
-            vep_version           = '108.2'
         }
         'CHM13' {
             fasta                 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa"
@@ -123,11 +115,9 @@ params {
             readme                = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt"
             snpeff_db             = 99
             snpeff_genome         = 'GRCm38'
-            snpeff_version        = '5.1'
             vep_cache_version     = 102
             vep_genome            = 'GRCm38'
             vep_species           = 'mus_musculus'
-            vep_version           = '108.2'
         }
         'TAIR10' {
             bwa                   = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/"
@@ -145,34 +135,28 @@ params {
             readme                = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt"
             snpeff_db             = 75
             snpeff_genome         = 'UMD3.1'
-            snpeff_version        = '5.1'
             vep_cache_version     = 94
             vep_genome            = 'UMD3.1'
             vep_species           = 'bos_taurus'
-            vep_version           = '108.2'
         }
         'WBcel235' {
             bwa                   = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa"
             snpeff_db             = 105
             snpeff_genome         = 'WBcel235'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'WBcel235'
             vep_species           = 'caenorhabditis_elegans'
-            vep_version           = '108.2'
         }
         'CanFam3.1' {
             bwa                   = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa"
             readme                = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt"
             snpeff_db             = 99
             snpeff_genome         = 'CanFam3.1'
-            snpeff_version        = '5.1'
             vep_cache_version     = 104
             vep_genome            = 'CanFam3.1'
             vep_species           = 'canis_lupus_familiaris'
-            vep_version           = '108.2'
         }
         'GRCz10' {
             bwa                   = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/"
@@ -228,11 +212,9 @@ params {
             fasta                 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa"
             snpeff_db             = 105
             snpeff_genome         = 'R64-1-1'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'R64-1-1'
             vep_species           = 'saccharomyces_cerevisiae'
-            vep_version           = '108.2'
         }
         'EF2' {
             bwa                   = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/"
@@ -258,35 +240,29 @@ params {
             fasta                 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa"
             snpeff_db             = 105
             snpeff_genome         = 'GRCh38'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'GRCh38'
             vep_species           = 'homo_sapiens'
-            vep_version           = '108.2'
         }
         'hg19' {
             bwa                   = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa"
             readme                = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt"
             snpeff_db             = 87
             snpeff_genome         = 'GRCh37'
-            snpeff_version        = '5.1'
-            vep_cache_version     = 108
+            vep_cache_version     = 110
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
-            vep_version           = '108.2'
         }
         'mm10' {
             bwa                   = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa"
             readme                = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt"
             snpeff_db             = 99
             snpeff_genome         = 'GRCm38'
-            snpeff_version        = '5.1'
             vep_cache_version     = 102
             vep_genome            = 'GRCm38'
             vep_species           = 'mus_musculus'
-            vep_version           = '108.2'
         }
         'bosTau8' {
             bwa                   = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/version0.6.0/"

diff --git a/conf/modules/annotate.config b/conf/modules/annotate.config
@@ -20,7 +20,6 @@ process {
         withName: 'SNPEFF_SNPEFF' {
             ext.prefix       = { vcf.baseName - ".vcf" + "_snpEff" }
             ext.args         = '-nodownload -canon -v'
-            if (!params.snpeff_cache && !params.download_cache) container = { params.snpeff_genome ? "docker.io/nfcore/snpeff:${params.snpeff_version}.${params.snpeff_genome}" : "docker.io/nfcore/snpeff:${params.snpeff_version}.${params.genome}" }
             publishDir       = [
                 [
                     mode: params.publish_dir_mode,
@@ -46,7 +45,6 @@ process {
             ].join(' ').trim() }
             // If just VEP: <vcf prefix>_VEP.ann.vcf
             ext.prefix       = { vcf.baseName - ".vcf" + "_VEP.ann" }
-            if (!params.vep_cache && !params.download_cache)    container = { params.vep_genome ? "docker.io/nfcore/vep:${params.vep_version}.${params.vep_genome}" : "docker.io/nfcore/vep:${params.vep_version}.${params.genome}" }
             publishDir       = [
                 [
                     mode: params.publish_dir_mode,

diff --git a/conf/test.config b/conf/test.config
@@ -29,20 +29,20 @@ params {
     germline_resource = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz"
     intervals         = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.interval_list"
     known_indels      = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz"
+    snpeff_cache      = null
     snpeff_db         = 105
     snpeff_genome     = 'WBcel235'
-    snpeff_version    = '5.1'
-    vep_cache_version = 106
+    vep_cache         = null
+    vep_cache_version = 110
     vep_genome        = 'WBcel235'
     vep_species       = 'caenorhabditis_elegans'
-    vep_version       = '106.1'
 
     // default params
     split_fastq       = 0         // no FASTQ splitting
     tools             = 'strelka' // Variant calling with Strelka
 
     // Ignore params that will throw warning through params validation
-    validationSchemaIgnoreParams = 'genomes,snpeff_version,vep_version'
+    validationSchemaIgnoreParams = 'genomes'
 }
 
 process {

diff --git a/conf/test/cache.config b/conf/test/cache.config
@@ -41,20 +41,20 @@ params {
     germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz']
     intervals         = params.test_data['homo_sapiens']['genome']['genome_interval_list']
     known_indels      = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_vcf_gz']
+    snpeff_cache      = null
     snpeff_db         = 105
     snpeff_genome     = 'WBcel235'
-    snpeff_version    = '5.1'
-    vep_cache_version = 106
+    vep_cache         = null
+    vep_cache_version = 110
     vep_genome        = 'WBcel235'
     vep_species       = 'caenorhabditis_elegans'
-    vep_version       = '106.1'
 
     // default params
     split_fastq       = 0         // no FASTQ splitting
     tools             = 'strelka' // Variant calling with Strelka
 
     // Ignore params that will throw warning through params validation
-    validationSchemaIgnoreParams = 'genomes,test_data,snpeff_version,vep_version'
+    validationSchemaIgnoreParams = 'genomes,test_data'
 }
 
 process {

diff --git a/main.nf b/main.nf
@@ -56,11 +56,9 @@ params.pon                   = WorkflowMain.getGenomeAttribute(params, 'pon')
 params.pon_tbi               = WorkflowMain.getGenomeAttribute(params, 'pon_tbi')
 params.snpeff_db             = WorkflowMain.getGenomeAttribute(params, 'snpeff_db')
 params.snpeff_genome         = WorkflowMain.getGenomeAttribute(params, 'snpeff_genome')
-params.snpeff_version        = WorkflowMain.getGenomeAttribute(params, 'snpeff_version')
 params.vep_cache_version     = WorkflowMain.getGenomeAttribute(params, 'vep_cache_version')
 params.vep_genome            = WorkflowMain.getGenomeAttribute(params, 'vep_genome')
 params.vep_species           = WorkflowMain.getGenomeAttribute(params, 'vep_species')
-params.vep_version           = WorkflowMain.getGenomeAttribute(params, 'vep_version')
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

diff --git a/nextflow.config b/nextflow.config
@@ -73,24 +73,25 @@ params {
     sentieon_haplotyper_emit_mode = "variant" // default value for Sentieon haplotyper
 
     // Annotation
-    vep_out_format      = "vcf"
-    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
-    dbnsfp              = null  // No dbnsfp processed file
-    dbnsfp_tbi          = null  // No dbnsfp processed file index
-    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
-    vep_loftee          = null  // loftee plugin disabled within VEP
-    vep_spliceai        = null  // spliceai plugin disabled within VEP
-    spliceai_snv        = null  // No spliceai_snv file
-    spliceai_snv_tbi    = null  // No spliceai_snv file index
-    spliceai_indel      = null  // No spliceai_indel file
-    spliceai_indel_tbi  = null  // No spliceai_indel file index
-    vep_spliceregion    = null  // spliceregion plugin disabled within VEP
-    outdir_cache        = null  // No output directory for cache
-    snpeff_cache        = null  // No directory for snpEff cache
-    vep_cache           = null  // No directory for VEP cache
-    vep_include_fasta   = false // Don't use fasta file for annotation with VEP
+    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
+    snpeff_cache              = 's3://annotation-cache/snpeff_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
+    use_annotation_cache_keys = true
+    vep_cache                 = 's3://annotation-cache/vep_cache/'
+    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
 
     // MultiQC options
     multiqc_config             = null
@@ -128,7 +129,7 @@ params {
     // Schema validation default options
     validationFailUnrecognisedParams = false
     validationLenientMode            = true
-    validationSchemaIgnoreParams     = 'genomes,snpeff_version,vep_version,cf_ploidy'
+    validationSchemaIgnoreParams     = 'genomes,cf_ploidy'
     validationShowHiddenParams       = false
     validate_params                  = true
 }

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -508,16 +508,24 @@
                     "hidden": true,
                     "help_text": "Using this params you can add custom args to VEP."
                 },
+                "use_annotation_cache_keys": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-toolbox",
+                    "description": "Use annotation cache keys for snpeff_cache and vep_cache.",
+                    "hidden": true
+                },
                 "snpeff_cache": {
                     "type": "string",
                     "fa_icon": "fas fa-file",
+                    "default": "s3://annotation-cache/snpeff_cache/",
                     "description": "Path to snpEff cache.",
                     "help_text": "To be used with `--annotation_cache`.",
                     "hidden": true
                 },
                 "vep_cache": {
                     "type": "string",
                     "fa_icon": "fas fa-file",
+                    "default": "s3://annotation-cache/vep_cache/",
                     "description": "Path to VEP cache.",
                     "help_text": "To be used with `--annotation_cache`.",
                     "hidden": true
@@ -729,13 +737,6 @@
                     "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the genome when using the container with pre-downloaded cache.",
                     "hidden": true
                 },
-                "snpeff_version": {
-                    "type": "string",
-                    "fa_icon": "fas fa-tag",
-                    "description": "snpEff version.",
-                    "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the snpeff version when using the container with pre-downloaded cache.",
-                    "hidden": true
-                },
                 "vep_genome": {
                     "type": "string",
                     "fa_icon": "fas fa-microscope",
@@ -757,13 +758,6 @@
                     "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nAlternatively cache version can be use to specify the correct Ensembl Genomes version number as these differ from the concurrent Ensembl/VEP version numbers",
                     "hidden": true
                 },
-                "vep_version": {
-                    "type": "string",
-                    "fa_icon": "fas fa-tag",
-                    "description": "VEP version.",
-                    "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the VEP version when using the container with pre-downloaded cache.",
-                    "hidden": true
-                },
                 "save_reference": {
                     "type": "boolean",
                     "fa_icon": "fas fa-download",

diff --git a/tests/test_annotation_cache.yml b/tests/test_annotation_cache.yml
@@ -9,29 +9,3 @@
     - path: results/cache/vep_cache
     - path: results/annotation
       should_exist: false
-- name: Download annotation cache and annotate using snpEff and VEP
-  command: nextflow run main.nf -profile test_cache,annotation --tools snpeff,vep --download_cache --outdir results
-  tags:
-    - annotation
-    - cache
-  files:
-    - path: results/multiqc
-    - path: results/cache/snpeff_cache
-    - path: results/cache/vep_cache
-    - path: results/annotation/test/test_VEP.ann.vcf.gz
-    # conda changes md5sums for test
-    - path: results/annotation/test/test_VEP.ann.vcf.gz.tbi
-    # conda changes md5sums for test
-    - path: results/annotation/test/test_snpEff.ann.vcf.gz
-    # conda changes md5sums for test
-    - path: results/annotation/test/test_snpEff.ann.vcf.gz.tbi
-    # conda changes md5sums for test
-    - path: results/multiqc
-    - path: results/reports/EnsemblVEP/test/test_VEP.ann.summary.html
-    # text-based file changes md5sums on reruns
-    - path: results/reports/snpeff/test/snpEff_summary.html
-    # text-based file changes md5sums on reruns
-    - path: results/reports/snpeff/test/test_snpEff.csv
-    # text-based file changes md5sums on reruns
-    - path: results/reports/snpeff/test/test_snpEff.genes.txt
-      md5sum: 130536bf0237d7f3f746d32aaa32840a