refactored vcfanno (#1266)

* final refactor: using tarball instead

modules/vcfanno/main.nf

@@ -9,10 +9,12 @@ process VCFANNO {
 
     input:
     tuple val(meta), path(vcf), path(tbi)
-    path vcfanno_config
+    tuple val(meta), path(vcf_uncompressed)
+    path toml
+    path resource_dir
 
     output:
-    tuple val(meta), path("*.vcf"), emit: vcf
+    tuple val(meta), path("*_annotated.vcf"), emit: vcf
     path "versions.yml"                     , emit: versions
 
     when:
@@ -21,12 +23,15 @@ process VCFANNO {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_vcf = vcf_uncompressed ?: vcf
     """
+    ln -sf $resource_dir/* \$(pwd)
+
     vcfanno \\
         -p $task.cpus \\
         $args \\
-        $vcfanno_config \\
+        $toml \\
-        $vcf \\
+        $input_vcf \\
         > ${prefix}_annotated.vcf
 
     cat <<-END_VERSIONS > versions.yml

modules/vcfanno/meta.yml

@@ -5,6 +5,8 @@ keywords:
   - bed
   - annotate
   - variant
+  - lua
+  - toml
 tools:
   - vcfanno:
       description: annotate a VCF with other VCFs/BEDs/tabixed files
@@ -23,19 +25,21 @@ input:
   - vcf:
       type: file
       description: query VCF file
-      pattern: "*.{vcf.gz}"
+      pattern: "*.{vcf, vcf.gz}"
-  - vcf.tbi:
+  - vcf_tabix:
       type: file
-      description: query VCF file index
+      description: tabix index of query VCF - only needed if vcf is compressed
-      pattern: "*.{vcf.gz.tbi}"
+      pattern: "*.vcf.gz.tbi"
-  - vcfanno_config:
+  - toml:
+      type: file
+      description: configuration file
+      pattern: "*.toml"
+  - resource_dir:
       type: file
       description: |
-        A simple configuration file is used to specify both the source files
+        This directory contains referenced files in the TOML config,
-        and the set of attributes (in the case of VCF)
+        and the corresponding indicies e.g. exac.vcf.gz + exac.vcf.gz.tbi,
-        or columns (in the case of BED or other tab-delimited formats)
+        with exception to the lua file.
-        that should be added to the query file.
-      pattern: "*.{toml}"
 
 output:
   - meta:
@@ -50,7 +54,7 @@ output:
   - vcf:
       type: file
       description: Annotated VCF file
-      pattern: "*.{vcf}"
+      pattern: "*.vcf"
 
 authors:
   - "@projectoriented"

tests/config/test_data.config

@@ -155,6 +155,8 @@ params {
                 justhusky_minimal_vcf_gz                       = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/ped/justhusky_minimal.vcf.gz"
                 justhusky_minimal_vcf_gz_tbi                   = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/ped/justhusky_minimal.vcf.gz.tbi"
                 
+                vcfanno_tar_gz                                 = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/vcfanno/vcfanno_grch38_module_test.tar.gz"
+                vcfanno_toml                                   = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/vcfanno/vcfanno.toml"
             }
             'pangenome' {
                 pangenome_fa                                  = "${test_data_dir}/pangenomics/homo_sapiens/pangenome.fa"

tests/modules/vcfanno/main.nf

@@ -2,18 +2,40 @@
 
 nextflow.enable.dsl = 2
 
+include { UNTAR } from '../../../modules/untar/main.nf'
 include { VCFANNO } from '../../../modules/vcfanno/main.nf'
 
 workflow test_vcfanno {
     
     input = [ 
-        [ id:'test', single_end:false ], // meta map
+        [ id:'test_compressed', single_end:false ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
         file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)
     ]
     
-    toml = file("https://raw.githubusercontent.com/nf-core/test-datasets/8fbd9f99a2feb3f9e39cd3bcdc4a9176a5835673/data/delete_me/vcfanno.toml", 
+    input_2 = [ [ id:'test_compressed', single_end:false ], // meta map 
-                checkIfExists: true)
+                [] ]
 
-    VCFANNO ( input, toml )
+    toml = file(params.test_data['homo_sapiens']['genome']['vcfanno_toml'], checkIfExists: true)
+    resource_dir = file(params.test_data['homo_sapiens']['genome']['vcfanno_tar_gz'], checkIfExists: true)
+
+    UNTAR ( resource_dir )
+    VCFANNO ( input, input_2, toml, UNTAR.out.untar )
+}
+
+workflow test_vcfanno_uncompressed {
+
+    input = [ [ id:'test_uncompressed', single_end:false ], // meta map
+                [] ,[] ]
+    
+    input_2 = [ 
+        [ id:'test_uncompressed', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
+    ]
+
+    toml = file(params.test_data['homo_sapiens']['genome']['vcfanno_toml'], checkIfExists: true)
+    resource_dir = file(params.test_data['homo_sapiens']['genome']['vcfanno_tar_gz'], checkIfExists: true)
+
+    UNTAR ( resource_dir )
+    VCFANNO ( input, input_2, toml, UNTAR.out.untar )
 }

tests/modules/vcfanno/test.yml

@@ -3,7 +3,21 @@
   tags:
     - vcfanno
   files:
-    - path: output/vcfanno/test_annotated.vcf
+    - path: output/untar/versions.yml
-      md5sum: 34259cf6b0a4698a2917ad3554b50c0f
+      md5sum: 6de038155bccbe4d264d09529bf9f4d8
+    - path: output/vcfanno/test_compressed_annotated.vcf
+      md5sum: 90ceb2fd2e06e781846d69c3981db665
     - path: output/vcfanno/versions.yml
       md5sum: 62d13540503b22f04a2280c91942cb03
+
+- name: vcfanno test_vcfanno_uncompressed
+  command: nextflow run tests/modules/vcfanno -entry test_vcfanno_uncompressed -c tests/config/nextflow.config
+  tags:
+    - vcfanno
+  files:
+    - path: output/untar/versions.yml
+      md5sum: a0de70274caac0cca31b077a1e7172d9
+    - path: output/vcfanno/test_uncompressed_annotated.vcf
+      md5sum: 90ceb2fd2e06e781846d69c3981db665
+    - path: output/vcfanno/versions.yml
+      md5sum: 300218dad68c3ffcc4783daa4f7c5a43