ADD argNorm module (nf-core#5905)

* ADD argnorm module * ENH correct pattern for 'hamronized' input * ENH specify hamronization command in script * ENH don't pass 'hamronized' as val * Fixed trailing whitespace * "single_end" is not relevant in this module * alignment * "db_args" to avoid any confusion with the input channel * Added a test to check $tool is provided * Implemented the stub mode * Added a test for the missing database * Reordered the arguments to match the script --------- Co-authored-by: Matthieu Muffato <[email protected]>
famosab · Jul 8, 2024 · e4fc46a · e4fc46a
1 parent c274982
commit e4fc46a
Show file tree

Hide file tree

Showing 8 changed files with 436 additions and 0 deletions.
diff --git a/modules/nf-core/argnorm/environment.yml b/modules/nf-core/argnorm/environment.yml
@@ -0,0 +1,7 @@
+name: "argnorm"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::argnorm=0.5.0"
diff --git a/modules/nf-core/argnorm/main.nf b/modules/nf-core/argnorm/main.nf
@@ -0,0 +1,68 @@
+process ARGNORM {
+    tag "$meta.id"
+    label 'process_low'
+    // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions.
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/argnorm:0.5.0--pyhdfd78af_0':
+        'biocontainers/argnorm:0.5.0--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(input_tsv)
+    val tool
+    val db
+
+    output:
+    tuple val(meta), path("*.tsv"), emit: tsv
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '0.5.0' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    def db_args = db ? "--db ${db}" : ""
+    if (!tool) {
+        error 'Tool not provided.'
+    }
+    if ((tool in ["abricate"]) && !db) {
+        error "$tool requires a database but <db> not provided."
+    }
+
+    """
+    argnorm \\
+        $tool \\
+        -i $input_tsv \\
+        -o $prefix \\
+        $db_args \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        argnorm: $VERSION
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '0.5.0' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    if (!tool) {
+        error 'Tool not provided.'
+    }
+    if ((tool in ["abricate"]) && !db) {
+        error "$tool requires a database but <db> not provided."
+    }
+
+    """
+    touch ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        argnorm: $VERSION
+    END_VERSIONS
+    """
+
+}
diff --git a/modules/nf-core/argnorm/meta.yml b/modules/nf-core/argnorm/meta.yml
@@ -0,0 +1,60 @@
+name: "argnorm"
+description: Normalize antibiotic resistance genes (ARGs) using the ARO ontology (developed by CARD).
+keywords:
+  - amr
+  - antimicrobial resistance
+  - arg
+  - antimicrobial resistance genes
+  - genomics
+  - metagenomics
+  - normalization
+  - drug categorization
+tools:
+  - "argnorm":
+      description: "Normalize antibiotic resistance genes (ARGs) using the ARO ontology (developed by CARD)."
+      homepage: "https://argnorm.readthedocs.io/en/latest/"
+      documentation: "https://argnorm.readthedocs.io/en/latest/"
+      tool_dev_url: "https://github.com/BigDataBiology/argNorm"
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+
+  - input_tsv:
+      type: file
+      description: ARG annotation output
+      pattern: "*.tsv"
+
+  - tool:
+      type: string
+      description: ARG annotation tool used
+      pattern: "argsoap|abricate|deeparg|resfinder|amrfinderplus"
+
+  - db:
+      type: string
+      description: Database used for ARG annotation
+      pattern: "sarg|ncbi|resfinder|deeparg|megares|argannot|resfinderfg"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - tsv:
+      type: file
+      description: Normalized argNorm output
+      pattern: "*.tsv"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@Vedanth-Ramji"
+maintainers:
+  - "@Vedanth-Ramji"
diff --git a/modules/nf-core/argnorm/tests/argnorm_hamronized.config b/modules/nf-core/argnorm/tests/argnorm_hamronized.config
@@ -0,0 +1,5 @@
+process {
+    withName: ARGNORM {
+        ext.args = '--hamronized'
+    }
+}
diff --git a/modules/nf-core/argnorm/tests/argnorm_raw.config b/modules/nf-core/argnorm/tests/argnorm_raw.config
@@ -0,0 +1,5 @@
+process {
+    withName: ARGNORM {
+        ext.args = ''
+    }
+}
diff --git a/modules/nf-core/argnorm/tests/main.nf.test b/modules/nf-core/argnorm/tests/main.nf.test
@@ -0,0 +1,155 @@
+nextflow_process {
+    name "Test Process ARGNORM"
+    script "../main.nf"
+    process "ARGNORM"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "argnorm"
+
+    test("argnorm - amrfinderplus_ncbi_raw - tsv") {
+        config './argnorm_raw.config'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'argnorm_raw.tsv' ], // meta map
+                    file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/amrfinderplus/test_output.tsv", checkIfExists: true)
+                ]
+                input[1] = 'amrfinderplus'
+                input[2] = 'ncbi'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("argnorm - amrfinderplus_ncbi_hamronized - tsv") {
+        config './argnorm_hamronized.config'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'argnorm_hamronized.tsv' ], // meta map
+                    file("https://raw.githubusercontent.com/BigDataBiology/argNorm/main/examples/hamronized/amrfinderplus.ncbi.orfs.tsv", checkIfExists: true)
+                ]
+                input[1] = 'amrfinderplus'
+                input[2] = 'ncbi'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("argnorm - missing tool") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'argnorm_raw.tsv' ], // meta map
+                    file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/amrfinderplus/test_output.tsv", checkIfExists: true)
+                ]
+                input[1] = []
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert !process.success },
+                { assert process.stdout.toString().contains("Tool not provided") }
+            )
+        }
+    }
+
+    test("argnorm - missing db") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'argnorm_raw.tsv' ], // meta map
+                    file("https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/amrfinderplus/test_output.tsv", checkIfExists: true)
+                ]
+                input[1] = "abricate"
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert !process.success },
+                { assert process.stdout.toString().contains("abricate requires a database but <db> not provided.") }
+            )
+        }
+    }
+
+    test("argnorm - amrfinderplus_ncbi_hamronized - tsv - stub") {
+        options "-stub"
+        config './argnorm_hamronized.config'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'argnorm_hamronized_stub.tsv'  ], // meta map
+                    file("https://raw.githubusercontent.com/BigDataBiology/argNorm/main/examples/hamronized/amrfinderplus.ncbi.orfs.tsv", checkIfExists: true)
+                ]
+                input[1] = 'amrfinderplus'
+                input[2] = 'ncbi'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+    test("argnorm - amrfinderplus_ncbi - tsv - stub") {
+
+        options "-stub"
+        config './argnorm_raw.config'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'argnorm_raw_stub.tsv' ], // meta map
+                    file("https://raw.githubusercontent.com/BigDataBiology/argNorm/main/examples/raw/amrfinderplus.ncbi.orfs.tsv", checkIfExists: true)
+                ]
+                input[1] = 'amrfinderplus'
+                input[2] = 'ncbi'
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+
+}