Proovframe update (#7158)

Ge94 · famosab · SPPearce · web-flow · commit 4f393faf4273 · 2025-11-07T17:29:52.000Z
* Separated input values because of meta

If the annotation file (faa) has been generated with an external db, meta values will be different between faa and fasta. This case is especially useful for proovframe, since it's main use is to be mapped to a set of high-quality proteins, usually coming from dbs like trembl or swissprot.

* Update proovframe main.nf.test with two input values

* Update return meta

Co-authored-by: Famke Bäuerle &lt;45968370+famosab@users.noreply.github.com&gt;

* Proovframe lint

* Adjust inputs, lint, tests

* Added meta2+3

* New test.snap

---------

Co-authored-by: Famke Bäuerle &lt;45968370+famosab@users.noreply.github.com&gt;
Co-authored-by: Simon Pearce &lt;24893913+SPPearce@users.noreply.github.com&gt;
diff --git a/modules/nf-core/proovframe/fix/environment.yml b/modules/nf-core/proovframe/fix/environment.yml
@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::proovframe=0.9.7
+  - "bioconda::proovframe=0.9.7"
diff --git a/modules/nf-core/proovframe/fix/meta.yml b/modules/nf-core/proovframe/fix/meta.yml
@@ -53,15 +53,15 @@ output:
           pattern: "*.{fa}"
           ontologies: []
   versions:
-    - versions.yml:
+    - "versions.yml":
         type: file
         description: File containing software versions
         pattern: "versions.yml"
-
         ontologies:
           - edam: http://edamontology.org/format_3750 # YAML
 authors:
   - "@mcarbajo"
   - "@vagkaratzas"
 maintainers:
   - "@vagkaratzas"
+  - "@Ge94"
diff --git a/modules/nf-core/proovframe/fix/tests/main.nf.test b/modules/nf-core/proovframe/fix/tests/main.nf.test
@@ -16,10 +16,14 @@ nextflow_process {
             process {
                 """
                 input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
+                    [ id:'fa', single_end:false ], // meta map
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
                 ]
+                input[1] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                input[2] = [[:], []]
                 """
             }
         }
diff --git a/modules/nf-core/proovframe/fix/tests/main.nf.test.snap b/modules/nf-core/proovframe/fix/tests/main.nf.test.snap
@@ -29,10 +29,10 @@
             }
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "23.04.5"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-10-18T12:17:51.685565164"
+        "timestamp": "2025-11-06T16:40:56.201526311"
     },
     "test - faa_fasta - stub": {
         "content": [
@@ -64,9 +64,9 @@
             }
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "23.04.5"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-10-18T12:17:57.181403559"
+        "timestamp": "2025-11-06T16:44:04.101218224"
     }
 }
diff --git a/modules/nf-core/proovframe/map/environment.yml b/modules/nf-core/proovframe/map/environment.yml
@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::proovframe=0.9.7
+  - "bioconda::proovframe=0.9.7"
diff --git a/modules/nf-core/proovframe/map/main.nf b/modules/nf-core/proovframe/map/main.nf
@@ -8,7 +8,9 @@ process PROOVFRAME_MAP {
         'biocontainers/proovframe:0.9.7--hdfd78af_1' }"
 
     input:
-    tuple val(meta), path(faa), path(fasta)
+    tuple val(meta), path(fasta)
+    tuple val(meta2), path(faa)
+    tuple val(meta3), path(db)
 
     output:
     tuple val(meta), path("*.tsv"), emit: tsv
@@ -20,12 +22,15 @@ process PROOVFRAME_MAP {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def db_type = db ? "--db ${db}" : (faa ? "--aa ${faa}" : "")
+
     """
     proovframe \\
         map \\
         ${args} \\
-        -a ${faa} \\
-        -o ${prefix}.tsv  \\
+        --threads ${task.cpus} \\
+        ${db_type} \\
+        -o ${prefix}.tsv \\
         ${fasta}
 
     cat <<-END_VERSIONS > versions.yml
diff --git a/modules/nf-core/proovframe/map/meta.yml b/modules/nf-core/proovframe/map/meta.yml
@@ -22,17 +22,32 @@ input:
         description: |
           Groovy Map containing sample information
           e.g. `[ id:'sample1', single_end:false ]`
-    - faa:
-        type: file
-        description: A FASTA file containing a database of guide protein sequences
-        pattern: "*.{faa,fasta,fa}"
-        ontologies: []
     - fasta:
         type: file
-        description: A FASTA file containing raw read nucleotide sequences
+        description: A FASTA fna file containing raw read nucleotide sequences
         pattern: "*.{fasta,fa}"
-
         ontologies: []
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - faa:
+          type: file
+          description: A proteome fasta file to create a database of guide protein sequences
+            from
+          pattern: "*.{faa,fasta,fa}"
+          ontologies: []
+  - - meta3:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+    - db:
+          type: file
+          description: A previously generated diamond database of guide protein sequences
+          pattern: "*.{dmnd}"
+          ontologies: []
 output:
   tsv:
     - - meta:
@@ -43,20 +58,21 @@ output:
       - "*.tsv":
           type: file
           description: Output TSV file with the frameshift-aware protein to read alignments
-          pattern: "*.tsv"
+          pattern: "*.{tsv}"
           ontologies:
             - edam: http://edamontology.org/format_3475 # TSV
   versions:
-    - versions.yml:
+    - "versions.yml":
         type: file
         description: File containing software versions
         pattern: "versions.yml"
-
         ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+          - edam: "http://edamontology.org/format_3750" # YAML
+
 authors:
   - "@manuelcarbajo"
   - "@MGS-sails"
   - "@vagkaratzas"
 maintainers:
   - "@vagkaratzas"
+  - "@Ge94"
diff --git a/modules/nf-core/proovframe/map/tests/main.nf.test b/modules/nf-core/proovframe/map/tests/main.nf.test
@@ -9,16 +9,51 @@ nextflow_process {
     tag "proovframe"
     tag "proovframe/map"
 
-    test("sarscov2 - tsv") {
+    test("sarscov2 - provided db") {
 
         when {
             process {
                 """
                 input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
+                    [ id:'fa', single_end:false ], // meta map
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
                 ]
+                input[1] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                input[2] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'proteomics/database/UP000005640_9606.dmnd', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.tsv[0][1]).text.contains('MT192765.1	sp|Q460N5|PAR14_HUMAN	28.4	176	105	5	3424	3918	818	983') },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+
+    }
+
+    test("sarscov2 - provided faa") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[1] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                input[2] = [[:], []]
                 """
             }
         }
@@ -40,10 +75,17 @@ nextflow_process {
             process {
                 """
                 input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
+                    [ id:'test2', single_end:false ], // meta map
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
                 ]
+                input[1] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)
+                ]
+                input[2] = [
+                    [ id:'fa', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'proteomics/database/UP000005640_9606.dmnd', checkIfExists: true)
+                ]
                 """
             }
         }
diff --git a/modules/nf-core/proovframe/map/tests/main.nf.test.snap b/modules/nf-core/proovframe/map/tests/main.nf.test.snap
@@ -1,26 +1,38 @@
 {
-    "sarscov2 - tsv": {
+    "sarscov2 - provided faa": {
         "content": [
             [
                 "versions.yml:md5,f49f29b8134fdb539364ee46855eb313"
             ]
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "23.04.5"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-10-18T12:19:19.854923441"
+        "timestamp": "2025-10-27T13:13:01.777154464"
+    },
+    "sarscov2 - provided db": {
+        "content": [
+            [
+                "versions.yml:md5,f49f29b8134fdb539364ee46855eb313"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
+        },
+        "timestamp": "2025-10-27T13:10:35.425578608"
     },
     "sarscov2 - tsv - stub": {
         "content": [
             {
                 "0": [
                     [
                         {
-                            "id": "test",
+                            "id": "test2",
                             "single_end": false
                         },
-                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "test2.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "1": [
@@ -29,10 +41,10 @@
                 "tsv": [
                     [
                         {
-                            "id": "test",
+                            "id": "test2",
                             "single_end": false
                         },
-                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        "test2.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "versions": [
@@ -41,9 +53,9 @@
             }
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "23.04.5"
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.4"
         },
-        "timestamp": "2024-10-18T12:19:25.120972507"
+        "timestamp": "2025-10-27T13:15:18.917890463"
     }
 }

Original file line number	Diff line number	Diff line change
`@@ -16,10 +16,14 @@ nextflow_process {`
`16`	`16`	`process {`
`17`	`17`	`"""`
`18`	`18`	`input[0] = [`
`19`		`- [ id:'test', single_end:false ], // meta map`
`20`		`- file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),`
	`19`	`+ [ id:'fa', single_end:false ], // meta map`
`21`	`20`	`file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)`
`22`	`21`	`]`
	`22`	`+ input[1] = [`
	`23`	`+ [ id:'fa', single_end:false ], // meta map`
	`24`	`+ file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true)`
	`25`	`+ ]`
	`26`	`+ input[2] = [[:], []]`
`23`	`27`	`"""`
`24`	`28`	`}`
`25`	`29`	`}`
Original file line number	Diff line number	Diff line change
`@@ -1,26 +1,38 @@`
`1`	`1`	`{`
`2`		`- "sarscov2 - tsv": {`
	`2`	`+ "sarscov2 - provided faa": {`
`3`	`3`	`"content": [`
`4`	`4`	`[`
`5`	`5`	`"versions.yml:md5,f49f29b8134fdb539364ee46855eb313"`
`6`	`6`	`]`
`7`	`7`	`],`
`8`	`8`	`"meta": {`
`9`		`- "nf-test": "0.9.0",`
`10`		`- "nextflow": "23.04.5"`
	`9`	`+ "nf-test": "0.9.2",`
	`10`	`+ "nextflow": "24.10.4"`
`11`	`11`	`},`
`12`		`- "timestamp": "2024-10-18T12:19:19.854923441"`
	`12`	`+ "timestamp": "2025-10-27T13:13:01.777154464"`
	`13`	`+ },`
	`14`	`+ "sarscov2 - provided db": {`
	`15`	`+ "content": [`
	`16`	`+ [`
	`17`	`+ "versions.yml:md5,f49f29b8134fdb539364ee46855eb313"`
	`18`	`+ ]`
	`19`	`+ ],`
	`20`	`+ "meta": {`
	`21`	`+ "nf-test": "0.9.2",`
	`22`	`+ "nextflow": "24.10.4"`
	`23`	`+ },`
	`24`	`+ "timestamp": "2025-10-27T13:10:35.425578608"`
`13`	`25`	`},`
`14`	`26`	`"sarscov2 - tsv - stub": {`
`15`	`27`	`"content": [`
`16`	`28`	`{`
`17`	`29`	`"0": [`
`18`	`30`	`[`
`19`	`31`	`{`
`20`		`- "id": "test",`
	`32`	`+ "id": "test2",`
`21`	`33`	`"single_end": false`
`22`	`34`	`},`
`23`		`- "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"`
	`35`	`+ "test2.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"`
`24`	`36`	`]`
`25`	`37`	`],`
`26`	`38`	`"1": [`
`@@ -29,10 +41,10 @@`
`29`	`41`	`"tsv": [`
`30`	`42`	`[`
`31`	`43`	`{`
`32`		`- "id": "test",`
	`44`	`+ "id": "test2",`
`33`	`45`	`"single_end": false`
`34`	`46`	`},`
`35`		`- "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"`
	`47`	`+ "test2.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"`
`36`	`48`	`]`
`37`	`49`	`],`
`38`	`50`	`"versions": [`
`@@ -41,9 +53,9 @@`
`41`	`53`	`}`
`42`	`54`	`],`
`43`	`55`	`"meta": {`
`44`		`- "nf-test": "0.9.0",`
`45`		`- "nextflow": "23.04.5"`
	`56`	`+ "nf-test": "0.9.2",`
	`57`	`+ "nextflow": "24.10.4"`
`46`	`58`	`},`
`47`		`- "timestamp": "2024-10-18T12:19:25.120972507"`
	`59`	`+ "timestamp": "2025-10-27T13:15:18.917890463"`
`48`	`60`	`}`
`49`	`61`	`}`