New module - TD2 (added modules for td2.longorfs & td2.predict)

modules/nf-core/td2/longorfs/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::td2=1.0.6"

modules/nf-core/td2/longorfs/main.nf

@@ -0,0 +1,51 @@
+process TD2_LONGORFS {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/41/4155bf3b720e1e32d0615a947696fb0287ee4e8cdbeb4ec784dd4da7bb5b2e86/data':
+        "community.wave.seqera.io/library/td2:1.0.6--ea3e5ac09443b677"}"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("${prefix}/longest_orfs.{cds,gff3,pep}"), emit: orfs
+    path("versions.yml")                                          , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    TD2.LongOrfs \\
+    -t ${fasta} \\
+    -O ${prefix} \\
+    --threads ${task.cpus} \\
+    ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        td2: \$(td2 v1.0.6)
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    mkdir -p ${prefix}/
+    touch ${prefix}/longest_orfs.cds
+    touch ${prefix}/longest_orfs.gff3
+    touch ${prefix}/longest_orfs.pep
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        td2: \$(td2 v1.0.6)
+    END_VERSIONS
+    """
+}

modules/nf-core/td2/longorfs/meta.yml

@@ -0,0 +1,54 @@
+name: "td2_longorfs"
+description: TD2 identifies candidate coding regions within transcript
+  sequences, such as those generated by de novo RNA-Seq transcript assembly
+keywords:
+  - td2
+  - orfs
+  - longorfs
+  - transcripts
+tools:
+  - td2:
+      description: "TD2 identifies candidate coding regions within transcript sequences,
+        such as those generated by de novo RNA-Seq transcript assembly"
+      homepage: "https://github.com/Markusjsommer/TD2"
+      documentation: "https://github.com/Markusjsommer/TD2"
+      tool_dev_url: "https://github.com/Markusjsommer/TD2"
+      licence: ["MIT"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - fasta:
+        type: file
+        description: Fasta file containing the target transcript sequences
+        pattern: "*.{fasta}"
+        ontologies: []
+output:
+  orfs:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}/longest_orfs.{cds,gff3,pep}:
+          type: file
+          description: Files containing the longest ORFs predicted from the input
+            transcript sequences
+          pattern: "${prefix}/longest_orfs.{cds,gff3,pep}"
+          ontologies: []
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: "http://edamontology.org/format_3750" # YAML
+
+authors:
+  - "@khersameesh24"
+maintainers:
+  - "@khersameesh24"

modules/nf-core/td2/longorfs/tests/main.nf.test

@@ -0,0 +1,64 @@
+nextflow_process {
+
+    name "Test Process TD2_LONGORFS"
+    script "../main.nf"
+    process "TD2_LONGORFS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "td2"
+    tag "td2/longorfs"
+
+    test("td2.longorfs - transcriptome.fasta") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test_td2_longorfs' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/transcriptome.fasta', checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    process.out,
+                    path(process.out.versions[0]).yaml
+                ).match() }
+            )
+        }
+
+    }
+
+    test("td2.longorfs - transcriptome.fasta -stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test_td2_longorfs' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/transcriptome.fasta', checkIfExists: true),
+                ]
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assertAll(
+                { assert snapshot(
+                    process.out,
+                    path(process.out.versions[0]).yaml
+                ).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/td2/longorfs/tests/main.nf.test.snap

@@ -0,0 +1,94 @@
+{
+    "td2.longorfs - transcriptome.fasta": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test_td2_longorfs"
+                        },
+                        [
+                            "longest_orfs.cds:md5,4226fe196a4527f938e25061ffe7eaf6",
+                            "longest_orfs.gff3:md5,864ae9147b65d07eb9d79c0e42968e12",
+                            "longest_orfs.pep:md5,0151dac6998be924139a4f5a5a0c590b"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0856a2e8d28b454f9c3a768cd3451f1a"
+                ],
+                "orfs": [
+                    [
+                        {
+                            "id": "test_td2_longorfs"
+                        },
+                        [
+                            "longest_orfs.cds:md5,4226fe196a4527f938e25061ffe7eaf6",
+                            "longest_orfs.gff3:md5,864ae9147b65d07eb9d79c0e42968e12",
+                            "longest_orfs.pep:md5,0151dac6998be924139a4f5a5a0c590b"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0856a2e8d28b454f9c3a768cd3451f1a"
+                ]
+            },
+            {
+                "TD2_LONGORFS": {
+                    "td2": null
+                }
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.0"
+        },
+        "timestamp": "2025-11-27T09:33:10.428948889"
+    },
+    "td2.longorfs - transcriptome.fasta -stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test_td2_longorfs"
+                        },
+                        [
+                            "longest_orfs.cds:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "longest_orfs.gff3:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "longest_orfs.pep:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,0856a2e8d28b454f9c3a768cd3451f1a"
+                ],
+                "orfs": [
+                    [
+                        {
+                            "id": "test_td2_longorfs"
+                        },
+                        [
+                            "longest_orfs.cds:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "longest_orfs.gff3:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "longest_orfs.pep:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0856a2e8d28b454f9c3a768cd3451f1a"
+                ]
+            },
+            {
+                "TD2_LONGORFS": {
+                    "td2": null
+                }
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.0"
+        },
+        "timestamp": "2025-11-27T09:35:15.301277063"
+    }
+}

modules/nf-core/td2/predict/environment.yml

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "bioconda::td2=1.0.6"

modules/nf-core/td2/predict/main.nf

@@ -0,0 +1,55 @@
+process TD2_PREDICT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/41/4155bf3b720e1e32d0615a947696fb0287ee4e8cdbeb4ec784dd4da7bb5b2e86/data':
+        "community.wave.seqera.io/library/td2:1.0.6--ea3e5ac09443b677"}"
+
+    input:
+    tuple val(meta), path(fasta), path(orfs_dir, stageAs: 'orfs')
+
+    output:
+    tuple val(meta), path("${prefix}/*.TD2.{bed,cds,gff3,pep}"), emit: predictions
+    path("versions.yml")                                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    mkdir -p ${prefix}/
+
+    TD2.Predict \\
+        -t ${fasta} \\
+        -O ${orfs_dir} \\
+        ${args}
+
+    mv *.TD2.{bed,cds,gff3,pep} ${prefix}/
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        td2: \$(td2 v1.0.6)
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    mkdir -p ${prefix}/
+    touch ${prefix}/fakefile.TD2.bed
+    touch ${prefix}/fakefile.TD2.cds
+    touch ${prefix}/fakefile.TD2.gff3
+    touch ${prefix}/fakefile.TD2.pep
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        td2: \$(td2 v1.0.6)
+    END_VERSIONS
+    """
+}

modules/nf-core/td2/predict/meta.yml

@@ -0,0 +1,58 @@
+name: "td2_predict"
+description: TD2 identifies candidate coding regions within transcript
+  sequences, such as those generated by de novo RNA-Seq transcript assembly
+keywords:
+  - predict
+  - orfs
+  - coding regions
+  - td2.predict
+tools:
+  - "td2":
+      description: "TD2 identifies candidate coding regions within transcript sequences,
+        such as those generated by de novo RNA-Seq transcript assembly"
+      homepage: "https://github.com/Markusjsommer/TD2"
+      documentation: "https://github.com/Markusjsommer/TD2"
+      tool_dev_url: "https://github.com/Markusjsommer/TD2"
+      licence: ["MIT"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - fasta:
+        type: file
+        description: Transcripts fasta file
+        pattern: "*.{fasta}"
+        ontologies: []
+    - orfs_dir:
+        type: file
+        description: Directory containing the ORF prediction files generated by the `td2_longorfs` module
+        pattern: "orfs_dir/"
+        ontologies: []
+output:
+  predictions:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - ${prefix}/*.TD2.{bed,cds,gff3,pep}:
+          type: file
+          description: Files containing the TD2 ORF predictions for the input transcript sequences
+          pattern: "${prefix}/*.TD2.{bed,cds,gff3,pep}"
+          ontologies: []
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: "http://edamontology.org/format_3750" # YAML
+
+authors:
+  - "@khersameesh24"
+maintainers:
+  - "@khersameesh24"