Generate metadata CSV/TSV in modules instead of workflow body

conf/modules.config

@@ -144,6 +144,22 @@ process {
     // SUBMISSION AND MANIFEST GENERATION
     //
 
+    withName: 'CREATE_ASSEMBLY_METADATA_CSV' {
+        publishDir = [
+            path: { "${params.outdir}/${params.mode}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'CREATE_GENOME_METADATA_TSV' {
+        publishDir = [
+            path: { "${params.outdir}/genome_metadata" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'GENOME_UPLOAD' {
         publishDir = [
             path: { "${params.outdir}/${params.mode}/upload/manifests" },

modules/local/create_assembly_metadata_csv/main.nf

@@ -0,0 +1,52 @@
+process CREATE_ASSEMBLY_METADATA_CSV {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/31/31f1c42a25a80ebc296a0aa07d83b3f0e408f9f3c240f9375c55d9790576c1de/data' :
+        'community.wave.seqera.io/library/pip_pygments:37b2b421ce07e516' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("${meta.id}_assembly_metadata.csv"), emit: csv
+    path "versions.yml"                                      , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def run_accession = meta.run_accession ?: ''
+    def coverage = meta.coverage ?: ''
+    def assembler = meta.assembler ?: ''
+    def assembler_version = meta.assembler_version ?: ''
+    def sample = '' // Sample column left empty because co-assemblies are not supported
+
+    """
+    cat > ${meta.id}_assembly_metadata.csv << EOF
+Runs,Coverage,Assembler,Version,Filepath,Sample
+${run_accession},${coverage},${assembler},${assembler_version},${fasta.name},${sample}
+EOF
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bash: \$(bash --version | head -n1 | sed 's/.*version //; s/ .*//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    cat > ${meta.id}_assembly_metadata.csv << EOF
+Runs,Coverage,Assembler,Version,Filepath,Sample
+${meta.run_accession ?: ''},${meta.coverage ?: ''},${meta.assembler ?: ''},${meta.assembler_version ?: ''},${fasta.name},
+EOF
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bash: \$(bash --version | head -n1 | sed 's/.*version //; s/ .*//')
+    END_VERSIONS
+    """
+}

modules/local/create_assembly_metadata_csv/meta.yml

@@ -0,0 +1,48 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "create_assembly_metadata_csv"
+description: Create input CSV metadata file for assembly_uploader tool
+keywords:
+  - assembly
+  - metadata
+  - ena
+  - submission
+tools:
+  - bash:
+      description: Bash shell scripting
+      homepage: https://www.gnu.org/software/bash/
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information:
+          - id: Sample identifier
+          - run_accession: ENA run accession
+          - coverage: Assembly coverage value
+          - assembler: Name of the assembler used
+          - assembler_version: Version of the assembler
+    - fasta:
+        type: file
+        description: Assembly FASTA file
+        pattern: "*.{fasta,fa,fna}"
+
+output:
+  - csv:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information (same as input)
+      - "*.csv":
+          type: file
+          description: CSV file containing assembly metadata to be used as input for the assembly_uploader
+          pattern: "*_assembly_metadata.csv"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+
+authors:
+  - "@ochkalova"
+maintainers:
+  - "@ochkalova"

modules/local/create_assembly_metadata_csv/tests/main.nf.test

@@ -0,0 +1,93 @@
+nextflow_process {
+
+    name "Test Process CREATE_ASSEMBLY_METADATA_CSV"
+    script "../main.nf"
+    process "CREATE_ASSEMBLY_METADATA_CSV"
+
+    tag "modules"
+    tag "modules_local"
+    tag "create_assembly_metadata_csv"
+
+    test("test_create_assembly_metadata_csv - complete metadata") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [
+                        id: 'test_sample',
+                        run_accession: 'ERR123456',
+                        coverage: 50.5,
+                        assembler: 'metaspades',
+                        assembler_version: '3.15.5'
+                    ],
+                    file('https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz')
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("test_create_assembly_metadata_csv - minimal metadata") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [
+                        id: 'minimal_sample'
+                    ],
+                    file('https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz')
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("test_create_assembly_metadata_csv - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [
+                        id: 'stub_sample',
+                        run_accession: 'ERR999999',
+                        coverage: 75.0,
+                        assembler: 'megahit',
+                        assembler_version: '1.2.9'
+                    ],
+                    file('https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/genome/NC_045512.2/GCF_009858895.2_ASM985889v3_genomic.200409.fna.gz')
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/local/create_genome_metadata_tsv/main.nf

@@ -0,0 +1,48 @@
+process CREATE_GENOME_METADATA_TSV {
+    tag "${meta.id}"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'oras://community.wave.seqera.io/library/bash:5.2.26' :
+        'community.wave.seqera.io/library/bash:5.2.26'}"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    path "*.tsv"       , emit: tsv
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: 'genomes_metadata'
+    def co_assembly_value = meta.co_assembly == "Yes" ? "True" : "False"
+    def rna_presence_value = meta.RNA_presence == "Yes" ? "True" : "False"
+    """
+    # Create header
+    echo -e "genome_name\\tgenome_path\\taccessions\\tassembly_software\\tbinning_software\\tbinning_parameters\\tstats_generation_software\\tcompleteness\\tcontamination\\tgenome_coverage\\tmetagenome\\tco-assembly\\tbroad_environment\\tlocal_environment\\tenvironmental_medium\\trRNA_presence\\tNCBI_lineage" > ${prefix}.tsv
+
+    # Add data row
+    echo -e "${meta.id}\\t${fasta.getName()}\\t${meta.accession}\\t${meta.assembly_software}\\t${meta.binning_software}\\t${meta.binning_parameters}\\t${meta.stats_generation_software}\\t${meta.completeness}\\t${meta.contamination}\\t${meta.genome_coverage}\\t${meta.metagenome}\\t${co_assembly_value}\\t${meta.broad_environment}\\t${meta.local_environment}\\t${meta.environmental_medium}\\t${rna_presence_value}\\t${meta.NCBI_lineage}" >> ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bash: \$(bash --version | head -n 1 | sed 's/GNU bash, version //; s/ .*//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: 'genomes_metadata'
+    """
+    echo -e "genome_name\\tgenome_path\\taccessions\\tassembly_software\\tbinning_software\\tbinning_parameters\\tstats_generation_software\\tcompleteness\\tcontamination\\tgenome_coverage\\tmetagenome\\tco-assembly\\tbroad_environment\\tlocal_environment\\tenvironmental_medium\\trRNA_presence\\tNCBI_lineage" > ${prefix}.tsv
+    echo -e "${meta.id}\\t${fasta.getName()}\\t${meta.accession}\\t${meta.assembly_software}\\t${meta.binning_software}\\t${meta.binning_parameters}\\t${meta.stats_generation_software}\\t${meta.completeness}\\t${meta.contamination}\\t${meta.genome_coverage}\\t${meta.metagenome}\\tTrue\\t${meta.broad_environment}\\t${meta.local_environment}\\t${meta.environmental_medium}\\tTrue\\t${meta.NCBI_lineage}" >> ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bash: \$(bash --version | head -n 1 | sed 's/GNU bash, version //; s/ .*//')
+    END_VERSIONS
+    """
+}

modules/local/create_genome_metadata_tsv/meta.yml

@@ -0,0 +1,60 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "create_genome_metadata_tsv"
+description: Creates a tab-separated TSV file containing metadata for genome MAGs/bins submissions
+keywords:
+  - genomics
+  - metadata
+  - submission
+  - metagenomics
+  - MAG
+  - bins
+tools:
+  - bash:
+      description: GNU Bourne-Again SHell
+      homepage: https://www.gnu.org/software/bash/
+      documentation: https://www.gnu.org/software/bash/manual/
+      licence: ["GPL-3.0-or-later"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing genome metadata. Required fields:
+            - id: Genome identifier
+            - accession: Sample accession
+            - assembly_software: Software used for assembly
+            - binning_software: Software used for binning
+            - binning_parameters: Parameters used for binning
+            - stats_generation_software: Software used for stats generation
+            - completeness: Genome completeness percentage
+            - contamination: Genome contamination percentage
+            - genome_coverage: Genome coverage value
+            - metagenome: Metagenome identifier
+            - co_assembly: Co-assembly status ("Yes" or other)
+            - broad_environment: Broad environmental context
+            - local_environment: Local environmental context
+            - environmental_medium: Environmental medium description
+            - RNA_presence: RNA presence status ("Yes" or other)
+            - NCBI_lineage: NCBI taxonomic lineage
+    - fasta:
+        type: file
+        description: Genome FASTA file
+        pattern: "*.{fasta,fa,fna}"
+
+output:
+  - tsv:
+      - "*.tsv":
+          type: file
+          description: Tab-separated TSV file with genome metadata
+          pattern: "*.tsv"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+
+authors:
+  - "@ochkalova"
+maintainers:
+  - "@ochkalova"