Update dsh-bio to version 2.0.7, add support for compressed GFA 1.0 format (#1207)

* Update dsh-bio to version 2.0.7, add support for compressed GFA 1.0 format

* fix ci failures

Co-authored-by: Chris Cheshire <chris.j.cheshire@gmail.com>

modules/dshbio/exportsegments/main.nf

@@ -2,16 +2,16 @@ process DSHBIO_EXPORTSEGMENTS {
     tag "${meta.id}"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.6" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.6--hdfd78af_0' :
-        'quay.io/biocontainers/dsh-bio:2.0.6--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
+        'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(gfa)
 
     output:
-    tuple val(meta), path("*.fa"), emit: fasta
+    tuple val(meta), path("*.fa.gz"), emit: fasta
     path "versions.yml"              , emit: versions
 
     script:
@@ -22,7 +22,7 @@ process DSHBIO_EXPORTSEGMENTS {
         export-segments \\
         $args \\
         -i $gfa \\
-        -o ${prefix}.fa
+        -o ${prefix}.fa.gz
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/dshbio/exportsegments/meta.yml

@@ -21,8 +21,8 @@ input:
             e.g. [ id:'test', single_end:false ]
     - gfa:
         type: file
-        description: Assembly segments in GFA 1.0 format
-        pattern: "*.{gfa}"
+        description: Assembly segments in uncompressed or compressed GFA 1.0 format
+        pattern: "*.{gfa|gfa.bgz|gfa.gz|gfa.zst}"
 output:
     - meta:
         type: map
@@ -31,8 +31,8 @@ output:
             e.g. [ id:'test', single_end:false ]
     - fasta:
         type: file
-        description: Assembly segment sequences in FASTA format
-        pattern: "*.{fa}"
+        description: Assembly segment sequences in gzipped FASTA format
+        pattern: "*.{fa.gz}"
     - versions:
         type: file
         description: File containing software versions

modules/dshbio/filterbed/main.nf

@@ -2,10 +2,10 @@ process DSHBIO_FILTERBED {
     tag "${meta.id}"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.6" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.6--hdfd78af_0' :
-        'quay.io/biocontainers/dsh-bio:2.0.6--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
+        'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bed)

modules/dshbio/filtergff3/main.nf

@@ -2,10 +2,10 @@ process DSHBIO_FILTERGFF3 {
     tag "${meta.id}"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.6" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.6--hdfd78af_0' :
-        'quay.io/biocontainers/dsh-bio:2.0.6--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
+        'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(gff3)

modules/dshbio/splitbed/main.nf

@@ -2,10 +2,10 @@ process DSHBIO_SPLITBED {
     tag "${meta.id}"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.6" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.6--hdfd78af_0' :
-        'quay.io/biocontainers/dsh-bio:2.0.6--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
+        'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(bed)

modules/dshbio/splitgff3/main.nf

@@ -2,10 +2,10 @@ process DSHBIO_SPLITGFF3 {
     tag "${meta.id}"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.6" : null)
+    conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.6--hdfd78af_0' :
-        'quay.io/biocontainers/dsh-bio:2.0.6--hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
+        'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
 
     input:
     tuple val(meta), path(gff3)

tests/config/test_data.config

@@ -82,6 +82,9 @@ params {
                 scaffolds_fasta                                = "${test_data_dir}/genomics/sarscov2/illumina/fasta/scaffolds.fasta"
 
                 assembly_gfa                                   = "${test_data_dir}/genomics/sarscov2/illumina/gfa/assembly.gfa"
+                assembly_gfa_bgz                               = "${test_data_dir}/genomics/sarscov2/illumina/gfa/assembly.gfa.bgz"
+                assembly_gfa_gz                                = "${test_data_dir}/genomics/sarscov2/illumina/gfa/assembly.gfa.gz"
+                assembly_gfa_zst                               = "${test_data_dir}/genomics/sarscov2/illumina/gfa/assembly.gfa.zst"
 
                 test_single_end_bam_readlist_txt               = "${test_data_dir}/genomics/sarscov2/illumina/picard/test.single_end.bam.readlist.txt"
 

tests/modules/dshbio/exportsegments/main.nf

@@ -11,3 +11,27 @@ workflow test_dshbio_exportsegments {
 
     DSHBIO_EXPORTSEGMENTS ( input )
 }
+
+workflow test_dshbio_exportsegments_bgz {
+    input = [ [ id:'test_bgz' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['assembly_gfa_bgz'], checkIfExists: true) ]
+            ]
+
+    DSHBIO_EXPORTSEGMENTS ( input )
+}
+
+workflow test_dshbio_exportsegments_gz {
+    input = [ [ id:'test_gz' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['assembly_gfa_gz'], checkIfExists: true) ]
+            ]
+
+    DSHBIO_EXPORTSEGMENTS ( input )
+}
+
+workflow test_dshbio_exportsegments_zst {
+    input = [ [ id:'test_zst' ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['assembly_gfa_zst'], checkIfExists: true) ]
+            ]
+
+    DSHBIO_EXPORTSEGMENTS ( input )
+}

tests/modules/dshbio/exportsegments/test.yml

@@ -4,5 +4,32 @@
     - dshbio
     - dshbio/exportsegments
   files:
-    - path: ./output/dshbio/test.fa
-      md5sum: 19ed0b69970ed3fbb641c5c510ebef61
+    - path: ./output/dshbio/test.fa.gz
+      md5sum: 2b8471e1ccf84169ccb75a1c1bb9109c
+
+- name: dshbio exportsegments bgz
+  command: nextflow run ./tests/modules/dshbio/exportsegments -entry test_dshbio_exportsegments_bgz -c ./tests/config/nextflow.config -c ./tests/modules/dshbio/exportsegments/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/exportsegments
+  files:
+    - path: ./output/dshbio/test_bgz.fa.gz
+      md5sum: 2b8471e1ccf84169ccb75a1c1bb9109c
+
+- name: dshbio exportsegments gz
+  command: nextflow run ./tests/modules/dshbio/exportsegments -entry test_dshbio_exportsegments_gz -c ./tests/config/nextflow.config -c ./tests/modules/dshbio/exportsegments/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/exportsegments
+  files:
+    - path: ./output/dshbio/test_gz.fa.gz
+      md5sum: 2b8471e1ccf84169ccb75a1c1bb9109c
+
+- name: dshbio exportsegments zst
+  command: nextflow run ./tests/modules/dshbio/exportsegments -entry test_dshbio_exportsegments_zst -c ./tests/config/nextflow.config -c ./tests/modules/dshbio/exportsegments/nextflow.config
+  tags:
+    - dshbio
+    - dshbio/exportsegments
+  files:
+    - path: ./output/dshbio/test_zst.fa.gz
+      md5sum: 2b8471e1ccf84169ccb75a1c1bb9109c