Update learnmsa module to work with compressed files. (#5276)

* add compression handling to learnmsa

* add compression simulation to stub

* fix typo

* commit tests

* remove duplicate snapshot names & regenerate

* Update modules/nf-core/learnmsa/align/meta.yml

Co-authored-by: Luisa Santus <[email protected]>

---------

Co-authored-by: Leon Rauschning <[email protected]>
Co-authored-by: Luisa Santus <[email protected]>

modules/nf-core/learnmsa/align/environment.yml

@@ -4,4 +4,5 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::learnmsa=1.3.2
+  - bioconda::learnmsa=2.0.1
+  - conda-forge::pigz=2.8

modules/nf-core/learnmsa/align/main.nf

@@ -4,43 +4,47 @@ process LEARNMSA_ALIGN {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/learnmsa:1.3.2--pyhdfd78af_0':
-        'biocontainers/learnmsa:1.3.2--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-741e0da5cf2d6d964f559672e2908c2111cbb46b:4930edd009376542543bfd2e20008bb1ae58f841-0' :
+        'biocontainers/mulled-v2-741e0da5cf2d6d964f559672e2908c2111cbb46b:4930edd009376542543bfd2e20008bb1ae58f841-0' }"
 
     input:
-    tuple val(meta),  path(fasta)
+    tuple val(meta), path(fasta)
+    val(compress)
 
     output:
-    tuple val(meta), path("*.aln"), emit: alignment
-    path "versions.yml"           , emit: versions
+    tuple val(meta), path("*.aln{.gz,}"), emit: alignment
+    path "versions.yml"                 , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def write_output = compress ? ">(pigz -cp ${task.cpus} > ${prefix}.aln.gz)" : "${prefix}.aln"
     """
     learnMSA \\
         $args \\
-        -i $fasta \\
-        -o ${prefix}.aln
+        -i <(unpigz -cdf $fasta) \\
+        -o $write_output
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         learnmsa: \$(learnMSA -h | grep 'version' | awk -F 'version ' '{print \$2}' | awk '{print \$1}' | sed 's/)//g')
+        pigz: \$(echo \$(pigz --version 2>&1) | sed 's/^.*pigz\\w*//' ))
     END_VERSIONS
     """
 
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch ${prefix}.aln
+    touch ${prefix}.aln${compress ? '.gz' : ''}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         learnmsa: \$(learnMSA -h | grep 'version' | awk -F 'version ' '{print \$2}' | awk '{print \$1}' | sed 's/)//g')
+        pigz: \$(echo \$(pigz --version 2>&1) | sed 's/^.*pigz\\w*//' ))
     END_VERSIONS
     """
 }

modules/nf-core/learnmsa/align/meta.yml

@@ -20,8 +20,11 @@ input:
         e.g. `[ id:'test']`
   - fasta:
       type: file
-      description: Input sequences in FASTA format
-      pattern: "*.{fa,fasta}"
+      description: Input sequences in FASTA format. May be gz-compressed or uncompressed.
+      pattern: "*.{fa,fasta}{.gz,}"
+  - compress:
+      type: boolean
+      description: Flag representing whether the output MSA should be compressed. Set to true to enable/false to disable compression. Compression is done using pigz, and is multithreaded.
 output:
   - meta:
       type: map
@@ -30,8 +33,8 @@ output:
         e.g. `[ id:'test']`
   - alignment:
       type: file
-      description: Alignment file.
-      pattern: "*.{aln}"
+      description: Alignment file, in FASTA format. May be gzipped or uncompressed.
+      pattern: "*.aln{.gz,}"
   - versions:
       type: file
       description: File containing software versions

modules/nf-core/learnmsa/align/tests/main.nf.test

@@ -10,14 +10,15 @@ nextflow_process {
     tag "learnmsa"
     tag "learnmsa/align"
 
-    test("sarscov2 - fasta") {
+    test("sarscov2 - fasta - uncompressed") {
 
         when {
             process {
                 """
                 input[0] = [ [ id:'test' ], // meta map
                              file(params.test_data['sarscov2']['genome']['informative_sites_fas'], checkIfExists: true)
                            ]
+                input[1] = false
                 """
             }
         }
@@ -26,10 +27,33 @@ nextflow_process {
             assertAll(
                 { assert process.success },
                 { assert path(process.out.alignment.get(0).get(1)).getText().contains(">sample1") },
-                { assert snapshot(process.out.versions).match("versions_structure") }
+                { assert snapshot(process.out.versions).match("versions") }
             )
         }
 
     }
 
-}
+    test("sarscov2 - fasta - compressed") {
+
+        when {
+            process {
+                """
+                input[0] = [ [ id:'test' ], // meta map
+                             file(params.test_data['sarscov2']['genome']['informative_sites_fas'], checkIfExists: true)
+                           ]
+                input[1] = true
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.alignment.get(0).get(1)).getTextGzip().contains(">sample1") },
+                { assert snapshot(process.out.versions).match("versions1") }
+            )
+        }
+
+    }
+
+}