Rename to correct module name, add meta and tets

modules/nf-core/catpack/cat/main.nf → modules/nf-core/catpack/contigs/main.nf

@@ -1,4 +1,4 @@
-process CATPACK_CAT {
+process CATPACK_CONTIGS {
     tag "${meta.id}"
     label 'process_medium'
 
@@ -9,13 +9,16 @@ process CATPACK_CAT {
 
     input:
     tuple val(meta), path(contigs)
-    path database
-    path taxonomy
+    tuple val(meta2), path(database)
+    tuple val(meta3), path(taxonomy)
 
     output:
     tuple val(meta), path("*.ORF2LCA.txt"), emit: orf2lca
     tuple val(meta), path("*.contig2classification.txt"), emit: contig2classification
     tuple val(meta), path("*.log"), emit: log
+    tuple val(meta), path("*.diamond"), emit: diamond
+    tuple val(meta), path("*.predicted_proteins.faa"), emit: faa
+    tuple val(meta), path("*.gff"), emit: gff
     path "versions.yml", emit: versions
 
     when:
@@ -25,14 +28,14 @@ process CATPACK_CAT {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    CAT_pack cat \\
-        ${args} \\
+    CAT_pack contigs \\
         -n ${task.cpus} \\
-        -o ${prefix}.bam \\
         -c ${contigs} \\
         -d ${database} \\
         -t ${taxonomy} \\
         -o ${prefix}
+        ${args} \\
+
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -46,6 +49,9 @@ process CATPACK_CAT {
     touch ${prefix}.ORF2LCA.txt
     touch ${prefix}.contig2classification.txt
     touch ${prefix}.log
+    touch ${prefix}.diamond
+    touch ${prefix}.predicted_proteins.faa
+    touch ${prefix}.predicted_proteins.gff
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/nf-core/catpack/contigs/meta.yml

@@ -0,0 +1,142 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "catpack_contigs"
+description: Taxonomic classification of long DNA sequences and metagenome assembled
+  genomes (e.g. contigs, MAGs / bins).
+keywords:
+  - taxonomic classification
+  - classification
+  - long reads
+  - mags
+  - assembly
+tools:
+  - "catpack":
+      description: "CAT/BAT: tool for taxonomic classification of contigs and metagenome-assembled
+        genomes (MAGs)"
+      homepage: "https://github.com/MGXlab/CAT_pack"
+      documentation: "https://github.com/MGXlab/CAT_pack"
+      tool_dev_url: "https://github.com/MGXlab/CAT_pack"
+      doi: "10.1186/s13059-019-1817-x"
+      licence: ["MIT"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+
+    - contigs:
+        type: file
+        description: A nucleotide FASTA file containing long DNA sequences such as contigs.
+        pattern: "*.{fasta,fna,fa,fas}"
+        ontologies:
+          - edam: "http://edamontology.org/format_1929"
+
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+
+    - database:
+        type: directory
+        description: Directory containing CAT_pack database files (e.g. output from
+          CAT_pack prepare)
+        pattern: "*./"
+        ontologies:
+          - edam: "http://edamontology.org/data_1049"
+
+  - - meta3:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+
+    - taxonomy:
+        type: directory
+        description: Directory containing CAT_pack taxonomy files (e.g. output from
+          CAT_pack prepare)
+        pattern: "*./"
+        ontologies:
+          - edam: "http://edamontology.org/data_1049"
+
+output:
+  - orf2lca:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.ORF2LCA.txt":
+          type: file
+          description: A TSV file with per-ORF hit stats and identified lineage
+          pattern: "*.ORF2LCA.txt"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  - contig2classification:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.contig2classification.txt":
+          type: file
+          description: A TSV file with per-contig hit stats and assignment justification
+            information
+          pattern: "*.contig2classification.txt"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  - log:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.log":
+          type: file
+          description: Log file with run messages and basic statistics
+          ontologies:
+            - edam: "http://edamontology.org/format_2330"
+  - diamond:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.diamond":
+          type: file
+          description: Intermediate DIAMOND TSV summary output file with alignment results
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  - faa:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.predicted_proteins.faa":
+          type: file
+          description: FAA file of DIAMOND predicted proteins hits
+          ontologies:
+            - edam: "http://edamontology.org/format_3475"
+  - gff:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1', single_end:false ]`
+      - "*.gff":
+          type: file
+          description: GFF file of DIAMOND predicted proteins hits
+          ontologies:
+            - edam: "http://edamontology.org/format_2305"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@jfy133"
+maintainers:
+  - "@jfy133"

modules/nf-core/catpack/cat/tests/main.nf.test → modules/nf-core/catpack/contigs/tests/main.nf.test

@@ -1,15 +1,14 @@
-// TODO nf-core: Once you have added the required tests, please run the following command to build this file:
-// nf-core modules test catpack/cat
 nextflow_process {
 
-    name "Test Process CATPACK_CAT"
+    name "Test Process CATPACK_CONTIGS"
     script "../main.nf"
-    process "CATPACK_CAT"
+    process "CATPACK_CONTIGS"
 
     tag "modules"
     tag "modules_nfcore"
     tag "catpack"
-    tag "catpack/cat"
+    tag "catpack/contigs"
+    tag "catpack/prepare"
 
     setup {
         run('CATPACK_PREPARE') {
@@ -25,7 +24,7 @@ nextflow_process {
         }
     }
 
-    test("sarscov2 - bam") {
+    test("sarscov2 - genome - fasta") {
 
         when {
             process {
@@ -40,37 +39,42 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out).match() }
-                //TODO nf-core: Add all required assertions to verify the test output.
-                // See https://nf-co.re/docs/contributing/tutorials/nf-test_assertions for more information and examples.
+                { assert snapshot (
+                        process.out.orf2lca,
+                        process.out.contig2classification,
+                        process.out.diamond,
+                        process.out.faa,
+                        process.out.gff,
+                        process.out.versions,
+                        path(process.out.log.get(0).get(1)).readLines().last().contains("CAT is done!")
+                    ).match()
+                }
             )
         }
 
     }
 
-    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used but keep the " - stub" suffix.
-    test("sarscov2 - bam - stub") {
+    test("sarscov2 - genome - fasta - stub") {
 
         options "-stub"
 
         when {
             process {
                 """
-                // TODO nf-core: define inputs of the process here. Example:
-
-                input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true),
-                ]
+                input[0] = [ [id:'test'], [ file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)  ] ]
+                input[1] = CATPACK_PREPARE.out.db
+                input[2] = CATPACK_PREPARE.out.taxonomy
                 """
             }
         }
 
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out).match() }
-                //TODO nf-core: Add all required assertions to verify the test output.
+                { assert snapshot(
+                        process.out
+                    ).match()
+                }
             )
         }