fix genome null with annotation

CHANGELOG.md

@@ -36,6 +36,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#942](https://github.com/nf-core/sarek/pull/942) - Update `README.md`
 - [#967](https://github.com/nf-core/sarek/pull/967) - Update and detail extensively how to use annotation cache
 - [#968](https://github.com/nf-core/sarek/pull/968) - Update all modules
+- [#1014](https://github.com/nf-core/sarek/pull/1014) - `snpeff_db` is now only the `db` version and not `genome.db`
 
 ### Fixed
 
@@ -48,12 +49,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#928](https://github.com/nf-core/sarek/pull/928) - Fix [#700](https://github.com/nf-core/sarek/issues/700)
 - [#929](https://github.com/nf-core/sarek/pull/929) - Fix somatic variant calling issues with msisensor following [#896](https://github.com/nf-core/sarek/pull/896)
 - [#941](https://github.com/nf-core/sarek/pull/941) - Fix json validation for `tools`, `skip_tools` and `use_gatk_spark` [#892](https://github.com/nf-core/sarek/issues/892)
-- [#954](https://github.com/nf-core/sarek/pull/954) - Fix missing annotation keys with snpeff and ensemblvep for `hg19`
+- [#954](https://github.com/nf-core/sarek/pull/954) - Fix missing annotation keys with `snpeff` and `ensemblvep` for `hg19`
 - [#957](https://github.com/nf-core/sarek/pull/957) - Add `failOnDuplicate` and `failOnMismatch` options to all `join()` operator where it was possible
 - [#982](https://github.com/nf-core/sarek/pull/982) - Remove usage of exit statements, using `Nextflow.error` instead
 - [#985](https://github.com/nf-core/sarek/pull/985) - Cache correctly identifies when it needs to be updated
 - [#988](https://github.com/nf-core/sarek/pull/988) - Updated ascat module to fix seed for reproducibility
 - [#998](https://github.com/nf-core/sarek/pull/998) - Remove parallelization within a sample for `Manta`
+- [#1014](https://github.com/nf-core/sarek/pull/1014) - Fix calls to `ensemblvep` and `snpeff` containers
 
 ### Deprecated
 

conf/igenomes.config

@@ -35,7 +35,7 @@ params {
             known_indels_tbi      = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/GATKBundle/{1000G_phase1,Mills_and_1000G_gold_standard}.indels.b37.vcf.gz.tbi"
             known_indels_vqsr     = '--resource:1000G,known=false,training=true,truth=true,prior=10.0 1000G_phase1.indels.b37.vcf.gz --resource:mills,known=false,training=true,truth=true,prior=10.0 Mills_and_1000G_gold_standard.indels.b37.vcf.gz'
             mappability           = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/Control-FREEC/out100m2_hg19.gem"
-            snpeff_db             = 'GRCh37.87'
+            snpeff_db             = 87
             snpeff_genome         = 'GRCh37'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -72,7 +72,7 @@ params {
             mappability           = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/Control-FREEC/out100m2_hg38.gem"
             pon                   = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz"
             pon_tbi               = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/GATKBundle/1000g_pon.hg38.vcf.gz.tbi"
-            snpeff_db             = 'GRCh38.105'
+            snpeff_db             = 105
             snpeff_genome         = 'GRCh38'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -84,7 +84,7 @@ params {
             bwa                   = "${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             = 'GRCh37.87'
+            snpeff_db             = 87
             snpeff_genome         = 'GRCh37'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -95,7 +95,7 @@ params {
         '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             = 'GRCh38.105'
+            snpeff_db             = 105
             snpeff_genome         = 'GRCh38'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -121,7 +121,7 @@ params {
             known_indels_tbi      = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/MouseGenomeProject/mgp.v5.merged.indels.dbSNP142.normed.vcf.gz.tbi"
             mappability           = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Control-FREEC/GRCm38_68_mm10.gem"
             readme                = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt"
-            snpeff_db             = 'GRCm38.99'
+            snpeff_db             = 99
             snpeff_genome         = 'GRCm38'
             snpeff_version        = '5.1'
             vep_cache_version     = 102
@@ -143,7 +143,7 @@ params {
             bwa                   = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa"
             readme                = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt"
-            snpeff_db             = 'UMD3.1.75'
+            snpeff_db             = 75
             snpeff_genome         = 'UMD3.1'
             snpeff_version        = '5.1'
             vep_cache_version     = 94
@@ -154,7 +154,7 @@ params {
         '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             = 'WBcel235.105'
+            snpeff_db             = 105
             snpeff_genome         = 'WBcel235'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -166,7 +166,7 @@ params {
             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                = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt"
-            snpeff_db             = 'CanFam3.1.99'
+            snpeff_db             = 99
             snpeff_genome         = 'CanFam3.1'
             snpeff_version        = '5.1'
             vep_cache_version     = 104
@@ -226,7 +226,7 @@ params {
         'R64-1-1' {
             bwa                   = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa"
-            snpeff_db             = 'R64-1-1.105'
+            snpeff_db             = 105
             snpeff_genome         = 'R64-1-1'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -256,7 +256,7 @@ params {
         'hg38' {
             bwa                   = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa"
-            snpeff_db             = 'GRCh38.105'
+            snpeff_db             = 105
             snpeff_genome         = 'GRCh38'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -268,7 +268,7 @@ params {
             bwa                   = "${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             = 'GRCh37.87'
+            snpeff_db             = 87
             snpeff_genome         = 'GRCh37'
             snpeff_version        = '5.1'
             vep_cache_version     = 108
@@ -280,7 +280,7 @@ params {
             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             = 'GRCm38.99'
+            snpeff_db             = 99
             snpeff_genome         = 'GRCm38'
             snpeff_version        = '5.1'
             vep_cache_version     = 102

conf/modules/annotate.config

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

conf/test/test.config

@@ -41,7 +41,7 @@ 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_db         = 'WBcel235.105'
+    snpeff_db         = 105
     snpeff_genome     = 'WBcel235'
     snpeff_version    = '5.1'
     vep_cache_version = 106

conf/test/test_full_germline.config

@@ -22,5 +22,4 @@ params {
 
     split_fastq = 50000000
     nucleotides_per_second = 100000
-
 }

nextflow_schema.json

@@ -681,7 +681,7 @@
                     "help_text": "If you use AWS iGenomes, this has already been set for you appropriately."
                 },
                 "snpeff_db": {
-                    "type": "string",
+                    "type": "number",
                     "fa_icon": "fas fa-database",
                     "description": "snpEff DB version.",
                     "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the database to be use to annotate with.\nAlternatively databases' names can be listed with the `snpEff databases`.",

workflows/sarek.nf

@@ -302,7 +302,7 @@ workflow SAREK {
     // Download cache if needed
     // Assuming that if the cache is provided, the user has already downloaded it
     ensemblvep_info = params.vep_cache ? [] : Channel.of([ [ id:"${params.vep_genome}.${params.vep_cache_version}" ], params.vep_genome, params.vep_species, params.vep_cache_version ])
-    snpeff_info = params.snpeff_cache ? [] : Channel.of([ [ id:params.snpeff_db ], params.snpeff_genome, params.snpeff_db.minus("${params.snpeff_genome}.") ])
+    snpeff_info = params.snpeff_cache ? [] : Channel.of([ [ id:"${params.snpeff_genome}.${params.snpeff_db}" ], params.snpeff_genome, params.snpeff_db ])
 
     if (params.download_cache) {
         PREPARE_CACHE(ensemblvep_info, snpeff_info)
@@ -1038,7 +1038,7 @@ workflow SAREK {
                 vcf_to_annotate,
                 vep_fasta,
                 params.tools,
-                snpeff_db,
+                params.snpeff_genome ? "${params.snpeff_genome}.${params.snpeff_db}" : "${params.genome}.${params.snpeff_db}",
                 snpeff_cache,
                 vep_genome,
                 vep_species,