bug fixes: genomicsdbimport (#1035)

* saving changes to checkout

* saving to sort out other branch

* removed yml tracking of files that cant be tracked due to directory name changing between runs

* test data added, ready for pr

* fix eol linting error

* Update modules/gatk4/genomicsdbimport/main.nf

Co-authored-by: Francesco L <53608000+lescai@users.noreply.github.com>

* merging with master

* update push to show progress

* tests now working untar able to pass data to genomicsdbimport

* commit to checkout

* tests updated, module reworked to simplify and emit updated gendb

* Apply suggestions from code review

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* update meta.yml 

Priority of input options changed, updated to reflect this

* Update test.yml

name prefix changed in main script, test.yml updated to reflect this

* fix tests due to review changes

* bug fixes, multicalling samples and gendb emissions now fixed

* Update pytest_modules.yml

* Update meta.yml

Co-authored-by: GCJMackenzie <gavin.mackenzie@nibsc.org>
Co-authored-by: Francesco L <53608000+lescai@users.noreply.github.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>
Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

modules/gatk4/genomicsdbimport/main.nf

@@ -25,18 +25,18 @@ process GATK4_GENOMICSDBIMPORT {
     val input_map
 
     output:
-    tuple val(meta), path("*_genomicsdb")   , optional:true, emit: genomicsdb
+    tuple val(meta), path("${prefix}")      , optional:true, emit: genomicsdb
     tuple val(meta), path("$updated_db")    , optional:true, emit: updatedb
     tuple val(meta), path("*.interval_list"), optional:true, emit: intervallist
     path "versions.yml"                                    , emit: versions
 
     script:
-    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
 
     // settings for running default create gendb mode
-    def inputs_command = input_map ? "--sample-name-map ${vcf[0]}" : "${'-V ' + vcf.join(' -V')}"
-    def dir_command = "--genomicsdb-workspace-path ${prefix}"
-    def intervals_command = intervalfile ? " -L ${intervalfile} " : " -L ${intervalval} "
+    inputs_command = input_map ? "--sample-name-map ${vcf[0]}" : "${'-V ' + vcf.join(' -V ')}"
+    dir_command = "--genomicsdb-workspace-path ${prefix}"
+    intervals_command = intervalfile ? " -L ${intervalfile} " : " -L ${intervalval} "
 
     // settings changed for running get intervals list mode if run_intlist is true
     if (run_intlist) {

modules/gatk4/genomicsdbimport/meta.yml

@@ -66,7 +66,11 @@ output:
   - genomicsdb:
       type: directory
       description: Directory containing the files that compose the genomicsdb workspace, this is only output for create mode, as update changes an existing db
-      pattern: "*_genomicsdb"
+      pattern: "*/$prefix"
+  - updatedb:
+      type: directory
+      description: Directory containing the files that compose the updated genomicsdb workspace, this is only output for update mode, and should be the same path as the input wspace.
+      pattern: "same/path/as/wspace"
   - intervallist:
       type: file
       description: File containing the intervals used to generate the genomicsdb, only created by get intervals mode.

tests/modules/gatk4/genomicsdbimport/main.nf

@@ -7,7 +7,7 @@ include { GATK4_GENOMICSDBIMPORT } from '../../../../modules/gatk4/genomicsdbimp
 
 workflow test_gatk4_genomicsdbimport_create_genomicsdb {
 
-    input = [ [ id:'test_genomicsdb'], // meta map
+    input = [ [ id:'test'], // meta map
               file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true) ,
               file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true) ,
               file(params.test_data['homo_sapiens']['genome']['genome_interval_list'], checkIfExists: true) ,
@@ -26,7 +26,7 @@ workflow test_gatk4_genomicsdbimport_get_intervalslist {
 
     UNTAR ( db )
 
-    def input = Channel.of([ [ id:'test_genomicsdb'], // meta map
+    def input = Channel.of([ [ id:'test'], // meta map
               [] ,
               [] ,
               [] ,
@@ -45,7 +45,7 @@ workflow test_gatk4_genomicsdbimport_update_genomicsdb {
 
     UNTAR ( db )
 
-    def input = Channel.of([ [ id:'test_genomicsdb'], // meta map
+    def input = Channel.of([ [ id:'test'], // meta map
               file( params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz'] , checkIfExists: true) ,
               file( params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz_tbi'] , checkIfExists: true) ,
               [] ,

tests/modules/gatk4/genomicsdbimport/test.yml

@@ -4,19 +4,19 @@
     - gatk4/genomicsdbimport
     - gatk4
   files:
-    - path: output/gatk4/test_genomicsdb/__tiledb_workspace.tdb
+    - path: output/gatk4/test/__tiledb_workspace.tdb
       md5sum: d41d8cd98f00b204e9800998ecf8427e
-    - path: output/gatk4/test_genomicsdb/callset.json
+    - path: output/gatk4/test/callset.json
       md5sum: a7d07d1c86449bbb1091ff29368da07a
-    - path: output/gatk4/test_genomicsdb/chr22$1$40001/.__consolidation_lock
+    - path: output/gatk4/test/chr22$1$40001/.__consolidation_lock
       md5sum: d41d8cd98f00b204e9800998ecf8427e
-    - path: output/gatk4/test_genomicsdb/chr22$1$40001/__array_schema.tdb
-    - path: output/gatk4/test_genomicsdb/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
+    - path: output/gatk4/test/chr22$1$40001/__array_schema.tdb
+    - path: output/gatk4/test/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
       md5sum: 2502f79658bc000578ebcfddfc1194c0
-    - path: output/gatk4/test_genomicsdb/vcfheader.vcf
-      contains: 
+    - path: output/gatk4/test/vcfheader.vcf
+      contains:
         - "FORMAT=<ID=AD,Number=R,Type=Integer,Description="
-    - path: output/gatk4/test_genomicsdb/vidmap.json
+    - path: output/gatk4/test/vidmap.json
       md5sum: 18d3f68bd2cb6f4474990507ff95017a
 
 - name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_get_intervalslist
@@ -25,7 +25,7 @@
     - gatk4/genomicsdbimport
     - gatk4
   files:
-    - path: output/gatk4/test_genomicsdb.interval_list
+    - path: output/gatk4/test.interval_list
       md5sum: 4c85812ac15fc1cd29711a851d23c0bf
 
 - name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_update_genomicsdb