Retire snpeff_genome

conf/igenomes.config

@@ -36,8 +36,7 @@ params {
             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           = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/Control-FREEC/out100m2_hg19.gem"
             ngscheckmate_bed      = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/NGSCheckMate/SNP_GRCh37_hg19_woChr.bed"
-            snpeff_db             = '87'
-            snpeff_genome         = 'GRCh37'
+            snpeff_db             = 'GRCh37.87'
             vep_cache_version     = '111'
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
@@ -73,8 +72,7 @@ params {
             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"
             sentieon_dnascope_model = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/Sentieon/SentieonDNAscopeModel1.1.model"
-            snpeff_db               = '105'
-            snpeff_genome           = 'GRCh38'
+            snpeff_db               = 'GRCh38.105'
             vep_cache_version       = '111'
             vep_genome              = 'GRCh38'
             vep_species             = 'homo_sapiens'
@@ -84,8 +82,7 @@ params {
             fasta                 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
             ngscheckmate_bed      = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/NGSCheckMate/SNP_GRCh37_hg19_woChr.bed"
             readme                = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt"
-            snpeff_db             = '87'
-            snpeff_genome         = 'GRCh37'
+            snpeff_db             = 'GRCh37.87'
             vep_cache_version     = '111'
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
@@ -94,8 +91,7 @@ params {
             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"
             ngscheckmate_bed      ="${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/NGSCheckMate/SNP_GRCh38_hg38_wChr.bed"
-            snpeff_db             = '105'
-            snpeff_genome         = 'GRCh38'
+            snpeff_db             = 'GRCh38.105'
             vep_cache_version     = '111'
             vep_genome            = 'GRCh38'
             vep_species           = 'homo_sapiens'
@@ -118,8 +114,7 @@ params {
             known_indels_tbi      = "${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             = '99'
-            snpeff_genome         = 'GRCm38'
+            snpeff_db             = 'GRCm38.99'
             vep_cache_version     = '102'
             vep_genome            = 'GRCm38'
             vep_species           = 'mus_musculus'
@@ -138,17 +133,15 @@ 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                = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt"
-            snpeff_db             = '75'
-            snpeff_genome         = 'UMD3.1'
+            snpeff_db             = 'UMD3.1.75'
             vep_cache_version     = '94'
             vep_genome            = 'UMD3.1'
             vep_species           = 'bos_taurus'
         }
         'WBcel235' {
             bwa                   = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/"
             fasta                 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa"
-            snpeff_db             = '105'
-            snpeff_genome         = 'WBcel235'
+            snpeff_db             = 'WBcel235.105'
             vep_cache_version     = '111'
             vep_genome            = 'WBcel235'
             vep_species           = 'caenorhabditis_elegans'
@@ -157,8 +150,7 @@ params {
             bwa                   = "${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             = '99'
-            snpeff_genome         = 'CanFam3.1'
+            snpeff_db             = 'CanFam3.1.99'
             vep_cache_version     = '104'
             vep_genome            = 'CanFam3.1'
             vep_species           = 'canis_lupus_familiaris'
@@ -215,8 +207,7 @@ 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             = '105'
-            snpeff_genome         = 'R64-1-1'
+            snpeff_db             = 'R64-1-1.105'
             vep_cache_version     = '111'
             vep_genome            = 'R64-1-1'
             vep_species           = 'saccharomyces_cerevisiae'
@@ -243,8 +234,7 @@ 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             = '105'
-            snpeff_genome         = 'GRCh38'
+            snpeff_db             = 'GRCh38.105'
             vep_cache_version     = '111'
             vep_genome            = 'GRCh38'
             vep_species           = 'homo_sapiens'
@@ -253,8 +243,7 @@ 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                = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt"
-            snpeff_db             = '87'
-            snpeff_genome         = 'GRCh37'
+            snpeff_db             = 'GRCh37.87'
             vep_cache_version     = '111'
             vep_genome            = 'GRCh37'
             vep_species           = 'homo_sapiens'
@@ -263,8 +252,7 @@ params {
             bwa                   = "${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             = '99'
-            snpeff_genome         = 'GRCm38'
+            snpeff_db             = 'GRCm38.99'
             vep_cache_version     = '102'
             vep_genome            = 'GRCm38'
             vep_species           = 'mus_musculus'
@@ -334,8 +322,7 @@ params {
             known_indels_tbi        = "${params.igenomes_base}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
             known_indels_vqsr       = '--resource:mills,known=false,training=true,truth=true,prior=10.0 mills_and_1000G.indels.vcf.gz'
             ngscheckmate_bed        = "${params.igenomes_base}/genomics/homo_sapiens/genome/chr21/germlineresources/SNP_GRCh38_hg38_wChr.bed"
-            snpeff_db               = '105'
-            snpeff_genome           = 'WBcel235'
+            snpeff_db               = 'WBcel235.105'
             vep_cache_version       = '111'
             vep_genome              = 'WBcel235'
             vep_species             = 'caenorhabditis_elegans'

docs/usage.md

@@ -898,16 +898,14 @@ By default all is specified in the [igenomes.config](https://github.com/nf-core/
 Explanation can be found for all params in the documentation:
 
 - [snpeff_db](https://nf-co.re/sarek/parameters#snpeff_db)
-- [snpeff_genome](https://nf-co.re/sarek/parameters#snpeff_genome)
 - [vep_genome](https://nf-co.re/sarek/parameters#vep_genome)
 - [vep_species](https://nf-co.re/sarek/parameters#vep_species)
 - [vep_cache_version](https://nf-co.re/sarek/parameters#vep_cache_version)
 
 With the previous example of `GRCh38`, these are the values that were used for these params:
 
 ```bash
-snpeff_db         = '105'
-snpeff_genome     = 'GRCh38'
+snpeff_db         = 'GRCh38.105'
 vep_cache_version = '110'
 vep_genome        = 'GRCh38'
 vep_species       = 'homo_sapiens'
@@ -1014,6 +1012,12 @@ This command could be used to point to the recently downloaded cache and run Snp
 nextflow run nf-core/sarek --outdir results --vep_cache /path_to/my-own-cache/vep_cache --snpeff_cache /path_to/my-own-cache/snpeff_cache --tools vep,snpeff --input samplesheet_vcf.csv
 ```
 
+Here is an example on how sarek may be used to download the SnpEff cache for Candida auris:
+
+```bash
+nextflow run nf-core/sarek --outdir results --outdir_cache /path_to/my-own-cache --tools snpeff --download_cache --build_only_index --input false --snpeff_db _candida_auris_gca_001189475 --step annotate --genome null --igenomes_ignore
+```
+
 ### Create containers with pre-downloaded cache
 
 nf-core is no longer maintaining containers with pre-downloaded cache. Hosting the cache within the container is not recommended as it can cause a number of problems. Instead we recommned using an external cache. The following is left for legacy reasons.

main.nf

@@ -56,7 +56,6 @@ params.pon                     = getGenomeAttribute('pon')
 params.pon_tbi                 = getGenomeAttribute('pon_tbi')
 params.sentieon_dnascope_model = getGenomeAttribute('sentieon_dnascope_model')
 params.snpeff_db               = getGenomeAttribute('snpeff_db')
-params.snpeff_genome           = getGenomeAttribute('snpeff_genome')
 params.vep_cache_version       = getGenomeAttribute('vep_cache_version')
 params.vep_genome              = getGenomeAttribute('vep_genome')
 params.vep_species             = getGenomeAttribute('vep_species')
@@ -235,7 +234,7 @@ workflow NFCORE_SAREK {
     if (params.download_cache) {
         // Assuming that even if the cache is provided, if the user specify download_cache, sarek will download the cache
         ensemblvep_info = Channel.of([ [ id:"${params.vep_cache_version}_${params.vep_genome}" ], params.vep_genome, params.vep_species, params.vep_cache_version ])
-        snpeff_info     = Channel.of([ [ id:"${params.snpeff_genome}.${params.snpeff_db}" ], params.snpeff_genome, params.snpeff_db ])
+        snpeff_info     = Channel.of([ [ id:"${params.snpeff_db}" ], params.snpeff_db ])
         DOWNLOAD_CACHE_SNPEFF_VEP(ensemblvep_info, snpeff_info)
         snpeff_cache = DOWNLOAD_CACHE_SNPEFF_VEP.out.snpeff_cache
         vep_cache    = DOWNLOAD_CACHE_SNPEFF_VEP.out.ensemblvep_cache.map{ meta, cache -> [ cache ] }
@@ -244,9 +243,8 @@ workflow NFCORE_SAREK {
     } else {
         // Looks for cache information either locally or on the cloud
         ANNOTATION_CACHE_INITIALISATION(
-            (params.snpeff_cache && params.tools && (params.tools.split(',').contains("snpeff") || params.tools.split(',').contains('merge'))),
+            (params.snpeff_db && params.tools && (params.tools.split(',').contains("snpeff") || params.tools.split(',').contains('merge'))),
             params.snpeff_cache,
-            params.snpeff_genome,
             params.snpeff_db,
             (params.vep_cache && params.tools && (params.tools.split(',').contains("vep") || params.tools.split(',').contains('merge'))),
             params.vep_cache,

nextflow_schema.json

@@ -766,12 +766,6 @@
                     "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`."
                 },
-                "snpeff_genome": {
-                    "type": "string",
-                    "fa_icon": "fas fa-microscope",
-                    "description": "snpEff genome.",
-                    "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the genome when looking for local cache, or cloud based cache."
-                },
                 "vep_genome": {
                     "type": "string",
                     "fa_icon": "fas fa-microscope",

subworkflows/local/annotation_cache_initialisation/main.nf

@@ -12,7 +12,6 @@ workflow ANNOTATION_CACHE_INITIALISATION {
     take:
     snpeff_enabled
     snpeff_cache
-    snpeff_genome
     snpeff_db
     vep_enabled
     vep_cache
@@ -24,8 +23,8 @@ workflow ANNOTATION_CACHE_INITIALISATION {
 
     main:
     if (snpeff_enabled) {
-        def snpeff_annotation_cache_key = (snpeff_cache == "s3://annotation-cache/snpeff_cache/") ? "${snpeff_genome}.${snpeff_db}/" : ""
-        def snpeff_cache_dir =  "${snpeff_annotation_cache_key}${snpeff_genome}.${snpeff_db}"
+        def snpeff_annotation_cache_key = (snpeff_cache == "s3://annotation-cache/snpeff_cache/") ? "${snpeff_db}/" : ""
+        def snpeff_cache_dir =  "${snpeff_annotation_cache_key}${snpeff_db}"
         def snpeff_cache_path_full = file("$snpeff_cache/$snpeff_cache_dir", type: 'dir')
         if ( !snpeff_cache_path_full.exists() || !snpeff_cache_path_full.isDirectory() ) {
             if (snpeff_cache == "s3://annotation-cache/snpeff_cache/") {
@@ -35,7 +34,7 @@ workflow ANNOTATION_CACHE_INITIALISATION {
             }
         }
         snpeff_cache = Channel.fromPath(file("${snpeff_cache}/${snpeff_annotation_cache_key}"), checkIfExists: true).collect()
-            .map{ cache -> [ [ id:"${snpeff_genome}.${snpeff_db}" ], cache ] }
+            .map{ cache -> [ [ id:"${snpeff_db}" ], cache ] }
     } else snpeff_cache = []
 
     if (vep_enabled) {

tests/test_annotation_cache.yml

@@ -21,7 +21,7 @@
   exit_code: 1
 
 - name: Fail to locate snpEff cache
-  command: nextflow run main.nf -profile test,annotation --snpeff_cache s3://annotation-cache/snpeff_cache/ --snpeff_genome na --tools snpeff --input false --build_only_index --outdir results
+  command: nextflow run main.nf -profile test,annotation --snpeff_cache s3://annotation-cache/snpeff_cache/ --snpeff_db na --tools snpeff --input false --build_only_index --outdir results
   tags:
     - annotation
     - cache

workflows/sarek/main.nf

@@ -874,7 +874,7 @@ workflow SAREK {
                 vcf_to_annotate.map{meta, vcf -> [ meta + [ file_name: vcf.baseName ], vcf ] },
                 vep_fasta,
                 params.tools,
-                params.snpeff_genome ? "${params.snpeff_genome}.${params.snpeff_db}" : "${params.genome}.${params.snpeff_db}",
+                params.snpeff_db,
                 snpeff_cache,
                 vep_genome,
                 vep_species,