feat(ribotish/predict): optional reference_gtf input + topics versions + 0.2.8

modules/nf-core/ribotish/predict/environment.yml

@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::ribotish=0.2.7
+  - bioconda::ribotish=0.2.8

modules/nf-core/ribotish/predict/main.nf

@@ -4,8 +4,8 @@ process RIBOTISH_PREDICT {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/ribotish:0.2.7--pyhdfd78af_0':
-        'quay.io/biocontainers/ribotish:0.2.7--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/ribotish:0.2.8--pyhdfd78af_0':
+        'quay.io/biocontainers/ribotish:0.2.8--pyhdfd78af_0' }"
 
     input:
     tuple val(meta), path(bam_ribo), path(bai_ribo)
@@ -14,19 +14,21 @@ process RIBOTISH_PREDICT {
     tuple val(meta4), path(candidate_orfs)
     tuple val(meta5), path(para_ribo)
     tuple val(meta6), path(para_ti)
+    tuple val(meta7), path(reference_gtf, stageAs: 'secondary.gtf')
 
     output:
     tuple val(meta), path("*_pred.txt")        , emit: predictions
     tuple val(meta), path("*_all.txt")         , emit: all
     tuple val(meta), path("*_transprofile.py") , emit: transprofile
-    path "versions.yml"                        , emit: versions
+    tuple val("${task.process}"), val('ribotish'), eval("ribotish --version | sed 's/ribotish //'"), topic: versions, emit: versions_ribotish
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference_gtf_arg = reference_gtf ? "-a ${reference_gtf}" : ''
 
     ribo_bam_cmd = ''
     ti_bam_cmd = ''
@@ -48,16 +50,12 @@ process RIBOTISH_PREDICT {
         $ti_bam_cmd \\
         -f $fasta \\
         -g $gtf \\
+        $reference_gtf_arg \\
         -o ${prefix}_pred.txt \\
         --allresult ${prefix}_all.txt \\
         --transprofile ${prefix}_transprofile.py \\
         -p $task.cpus \\
         $args
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        ribotish: \$(ribotish --version | sed 's/ribotish //')
-    END_VERSIONS
     """
 
     stub:
@@ -66,10 +64,5 @@ process RIBOTISH_PREDICT {
     touch ${prefix}_pred.txt
     touch ${prefix}_all.txt
     touch ${prefix}_transprofile.py
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        ribotish: \$(ribotish --version | sed 's/ribotish //')
-    END_VERSIONS
     """
 }

modules/nf-core/ribotish/predict/meta.yml

@@ -1,4 +1,3 @@
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "ribotish_predict"
 description: Quality control of riboseq bam data
 keywords:
@@ -13,9 +12,9 @@ tools:
       documentation: "https://github.com/zhpn1024/ribotish"
       tool_dev_url: "https://github.com/zhpn1024/ribotish"
       doi: "10.1038/s41467-017-01981-8"
-      licence: ["GPL v3"]
+      licence:
+        - "GPL v3"
       identifier: ""
-
 input:
   - - meta:
         type: map
@@ -85,7 +84,7 @@ input:
           Input P-site offset parameter files for riboseq bam files
         pattern: "*.py"
         ontologies:
-          - edam: http://edamontology.org/format_3996 # Python script
+          - edam: http://edamontology.org/format_3996
   - - meta6:
         type: map
         description: |
@@ -97,7 +96,20 @@ input:
           Input P-site offset parameter files for TI-seq bam files
         pattern: "*.py"
         ontologies:
-          - edam: http://edamontology.org/format_3996 # Python script
+          - edam: http://edamontology.org/format_3996
+  - - meta7:
+        type: map
+        description: |
+          Groovy Map containing reference information for the secondary
+          annotation file
+    - reference_gtf:
+        type: file
+        description: |
+          Optional secondary GTF annotation passed to ribotish as
+          `-a <reference-annotation>` (e.g. a MANE/RefSeq overlay applied on
+          top of the primary GTF). Pass `[]` to omit.
+        pattern: "*.gtf"
+        ontologies: []
 output:
   predictions:
     - - meta:
@@ -137,14 +149,28 @@ output:
             positions on transcript.
           pattern: "*.{py}"
           ontologies:
-            - edam: http://edamontology.org/format_3996 # Python script
+            - edam: http://edamontology.org/format_3996
+  versions_ribotish:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - ribotish:
+          type: string
+          description: The name of the tool
+      - ribotish --version | sed 's/ribotish //':
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
   versions:
-    - versions.yml:
-        type: file
-        description: File containing software versions
-        pattern: "versions.yml"
-        ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - ribotish:
+          type: string
+          description: The name of the tool
+      - ribotish --version | sed 's/ribotish //':
+          type: eval
+          description: The expression to obtain the version of the tool
 authors:
   - "@pinin4fjords"
 maintainers:

modules/nf-core/ribotish/predict/tests/main.nf.test

@@ -43,6 +43,7 @@ nextflow_process {
                 input[3] = Channel.of([[],[]])
                 input[4] = Channel.of([[],[]])
                 input[5] = Channel.of([[],[]])
+                input[6] = Channel.of([[],[]])
                 """
             }
         }
@@ -52,8 +53,10 @@ nextflow_process {
                 { assert process.success },
                 { assert path(process.out.predictions[0][1]).getText().contains("ENSG00000132640\tENST00000254977\tBTBD3\tprotein_coding\t20:11890767-11923666:+\tATG\t45\t1743\tExtended\t0\t0\tNone\t0.013377070461772932\tT\tNone\tNone\t0.02118962148347") },
                 { assert path(process.out.all[0][1]).getText().contains("ENSG00000132640\tENST00000254977\tBTBD3\tprotein_coding\t20:11890767-11923666:+\tATG\t45\t1743\tExtended\t0\t0\tNone\t0.013377070461772932\tT\tNone\tNone\t0.02118962148347") },
-                { assert snapshot(process.out.transprofile).match("transprofile_single_end_single_ribo_bam") },
-                { assert snapshot(process.out.versions).match("versions_single_end_single_ribo_bam") }
+                { assert snapshot(
+                    process.out.transprofile,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
             )
         }
     }
@@ -79,17 +82,20 @@ nextflow_process {
                 input[3] = Channel.of([[],[]])
                 input[4] = Channel.of([[],[]])
                 input[5] = Channel.of([[],[]])
+                input[6] = Channel.of([[],[]])
                 """
             }
         }
 
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out.predictions).match("predictions_single_end_single_ribo_bam_stub") },
-                { assert snapshot(process.out.all).match("all_single_end_single_ribo_bam_stub") },
-                { assert snapshot(process.out.transprofile).match("transprofile_single_end_single_ribo_bam_stub") },
-                { assert snapshot(process.out.versions).match("versions_single_end_single_ribo_bam_stub") }
+                { assert snapshot(
+                    process.out.predictions,
+                    process.out.all,
+                    process.out.transprofile,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
             )
         }
     }
@@ -119,6 +125,7 @@ nextflow_process {
                 input[3] = Channel.of([[],[]])
                 input[4] = Channel.of([[],[]])
                 input[5] = Channel.of([[],[]])
+                input[6] = Channel.of([[],[]])
                 """
             }
         }
@@ -128,8 +135,10 @@ nextflow_process {
                 { assert process.success },
                 { assert path(process.out.predictions[0][1]).getText().contains("ENSG00000284776\tENST00000618693\t\tprotein_coding\t20:18567478-18744216:+\tATG\t26\t695\tAnnotated\t0\t0\tNone\t0.0006123183014212") },
                 { assert path(process.out.all[0][1]).getText().contains("ENSG00000284776\tENST00000618693\t\tprotein_coding\t20:18567478-18744216:+\tATG\t26\t695\tAnnotated\t0\t0\tNone\t0.0006123183014212") },
-                { assert snapshot(process.out.transprofile).match("transprofile_single_end_multi_ribo_bam") },
-                { assert snapshot(process.out.versions).match("versions_single_end_multi_ribo_bam") }
+                { assert snapshot(
+                    process.out.transprofile,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
             )
         }
     }
@@ -161,17 +170,20 @@ nextflow_process {
                 input[3] = Channel.of([[],[]])
                 input[4] = Channel.of([[],[]])
                 input[5] = Channel.of([[],[]])
+                input[6] = Channel.of([[],[]])
                 """
             }
         }
 
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out.predictions).match("predictions_single_end_multi_ribo_bam_stub") },
-                { assert snapshot(process.out.all).match("all_single_end_multi_ribo_bam_stub") },
-                { assert snapshot(process.out.transprofile).match("transprofile_single_end_multi_ribo_bam_stub") },
-                { assert snapshot(process.out.versions).match("versions_single_end_multi_ribo_bam_stub") }
+                { assert snapshot(
+                    process.out.predictions,
+                    process.out.all,
+                    process.out.transprofile,
+                    process.out.findAll { key, val -> key.startsWith('versions') }
+                ).match() }
             )
         }
     }