Kallisto module

modules.json

@@ -1,41 +1,51 @@
 {
-    "name": "nf-core/lncpipe",
-    "homePage": "https://github.com/nf-core/lncpipe",
-    "repos": {
-        "https://github.com/nf-core/modules.git": {
-            "modules": {
-                "nf-core": {
-                    "fastqc": {
-                        "branch": "master",
-                        "git_sha": "08108058ea36a63f141c25c4e75f9f872a5b2296",
-                        "installed_by": ["modules"]
-                    },
-                    "multiqc": {
-                        "branch": "master",
-                        "git_sha": "f0719ae309075ae4a291533883847c3f7c441dad",
-                        "installed_by": ["modules"]
-                    }
-                }
-            },
-            "subworkflows": {
-                "nf-core": {
-                    "utils_nextflow_pipeline": {
-                        "branch": "master",
-                        "git_sha": "c2b22d85f30a706a3073387f30380704fcae013b",
-                        "installed_by": ["subworkflows"]
-                    },
-                    "utils_nfcore_pipeline": {
-                        "branch": "master",
-                        "git_sha": "51ae5406a030d4da1e49e4dab49756844fdd6c7a",
-                        "installed_by": ["subworkflows"]
-                    },
-                    "utils_nfschema_plugin": {
-                        "branch": "master",
-                        "git_sha": "2fd2cd6d0e7b273747f32e465fdc6bcc3ae0814e",
-                        "installed_by": ["subworkflows"]
-                    }
-                }
-            }
+  "name": "nf-core/lncpipe",
+  "homePage": "https://github.com/nf-core/lncpipe",
+  "repos": {
+    "https://github.com/nf-core/modules.git": {
+      "modules": {
+        "nf-core": {
+          "fastqc": {
+            "branch": "master",
+            "git_sha": "08108058ea36a63f141c25c4e75f9f872a5b2296",
+            "installed_by": ["modules"]
+          },
+          "kallisto/index": {
+            "branch": "master",
+            "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
+            "installed_by": ["modules"]
+          },
+          "kallisto/quant": {
+            "branch": "master",
+            "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
+            "installed_by": ["modules"]
+          },
+          "multiqc": {
+            "branch": "master",
+            "git_sha": "f0719ae309075ae4a291533883847c3f7c441dad",
+            "installed_by": ["modules"]
+          }
         }
+      },
+      "subworkflows": {
+        "nf-core": {
+          "utils_nextflow_pipeline": {
+            "branch": "master",
+            "git_sha": "c2b22d85f30a706a3073387f30380704fcae013b",
+            "installed_by": ["subworkflows"]
+          },
+          "utils_nfcore_pipeline": {
+            "branch": "master",
+            "git_sha": "51ae5406a030d4da1e49e4dab49756844fdd6c7a",
+            "installed_by": ["subworkflows"]
+          },
+          "utils_nfschema_plugin": {
+            "branch": "master",
+            "git_sha": "2fd2cd6d0e7b273747f32e465fdc6bcc3ae0814e",
+            "installed_by": ["subworkflows"]
+          }
+        }
+      }
     }
+  }
 }

modules/nf-core/kallisto/index/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::kallisto=0.51.1

modules/nf-core/kallisto/index/main.nf

@@ -0,0 +1,44 @@
+process KALLISTO_INDEX {
+    tag "$fasta"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kallisto:0.51.1--heb0cbe2_0':
+        'biocontainers/kallisto:0.51.1--heb0cbe2_0' }"
+
+    input:
+    tuple val(meta), path(fasta)
+
+    output:
+    tuple val(meta), path("kallisto")  , emit: index
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    kallisto \\
+        index \\
+        $args \\
+        -i kallisto \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kallisto: \$(echo \$(kallisto 2>&1) | sed 's/^kallisto //; s/Usage.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    mkdir kallisto
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kallisto: \$(echo \$(kallisto 2>&1) | sed 's/^kallisto //; s/Usage.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/kallisto/index/meta.yml

@@ -0,0 +1,46 @@
+name: kallisto_index
+description: Create kallisto index
+keywords:
+  - kallisto
+  - kallisto/index
+  - index
+tools:
+  - kallisto:
+      description: Quantifying abundances of transcripts from bulk and single-cell RNA-Seq
+        data, or more generally of target sequences using high-throughput sequencing
+        reads.
+      homepage: https://pachterlab.github.io/kallisto/
+      documentation: https://pachterlab.github.io/kallisto/manual
+      tool_dev_url: https://github.com/pachterlab/kallisto
+      licence: ["BSD-2-Clause"]
+      identifier: biotools:kallisto
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing reference information
+          e.g. [ id:'test' ]
+    - fasta:
+        type: file
+        description: genome fasta file
+        pattern: "*.{fasta}"
+output:
+  - index:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing reference information
+            e.g. [ id:'test' ]
+      - kallisto:
+          type: directory
+          description: Kallisto genome index
+          pattern: "*.idx"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@ggabernet"
+maintainers:
+  - "@ggabernet"

modules/nf-core/kallisto/index/tests/main.nf.test

@@ -0,0 +1,55 @@
+nextflow_process {
+
+    name "Test Process KALLISTO_INDEX"
+    script "../main.nf"
+    process "KALLISTO_INDEX"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "kallisto"
+    tag "kallisto/index"
+
+    test("sarscov2 transcriptome.fasta") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'transcriptome' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/transcriptome.fasta', checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert path(process.out.index.get(0).get(1)).exists() },
+                { assert snapshot(process.out.versions).match() }
+            )
+        }
+    }
+
+    test("sarscov2 transcriptome.fasta - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of([
+                    [ id:'transcriptome' ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/transcriptome.fasta', checkIfExists: true)
+                ])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/nf-core/kallisto/index/tests/main.nf.test.snap

@@ -0,0 +1,51 @@
+{
+    "sarscov2 transcriptome.fasta - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "transcriptome"
+                        },
+                        [
+
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,e23afe0f9a5d0dc20b05c27fe59ad041"
+                ],
+                "index": [
+                    [
+                        {
+                            "id": "transcriptome"
+                        },
+                        [
+
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,e23afe0f9a5d0dc20b05c27fe59ad041"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-19T18:51:55.402665844"
+    },
+    "sarscov2 transcriptome.fasta": {
+        "content": [
+            [
+                "versions.yml:md5,e23afe0f9a5d0dc20b05c27fe59ad041"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-10-19T18:51:42.328144373"
+    }
+}

modules/nf-core/kallisto/index/tests/tags.yml

@@ -0,0 +1,2 @@
+kallisto/index:
+  - modules/nf-core/kallisto/index/**

modules/nf-core/kallisto/quant/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::kallisto=0.51.1

modules/nf-core/kallisto/quant/main.nf

@@ -0,0 +1,84 @@
+process KALLISTO_QUANT {
+    tag "$meta.id"
+    label 'process_high'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/kallisto:0.51.1--heb0cbe2_0':
+        'biocontainers/kallisto:0.51.1--heb0cbe2_0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    tuple val(meta2), path(index)
+    path gtf
+    path chromosomes
+    val fragment_length
+    val fragment_length_sd
+
+    output:
+    tuple val(meta), path("${prefix}")        , emit: results
+    tuple val(meta), path("*.run_info.json")  , emit: json_info
+    tuple val(meta), path("*.log")            , emit: log
+    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}"
+    def gtf_input = gtf ? "--gtf ${gtf}" : ''
+    def chromosomes_input = chromosomes ? "--chromosomes ${chromosomes}" : ''
+
+    def single_end_params = ''
+    if (meta.single_end) {
+        if (!(fragment_length =~ /^\d+$/)) {
+            error "fragment_length must be set and numeric for single-end data"
+        }
+        if (!(fragment_length_sd =~ /^\d+$/)) {
+            error "fragment_length_sd must be set and numeric for single-end data"
+        }
+        single_end_params = "--single --fragment-length=${fragment_length} --sd=${fragment_length_sd}"
+    }
+
+    def strandedness = ''
+    if (!args.contains('--fr-stranded') && !args.contains('--rf-stranded')) {
+        strandedness =  (meta.strandedness == 'forward') ? '--fr-stranded' :
+                        (meta.strandedness == 'reverse') ? '--rf-stranded' : ''
+    }
+
+    """
+    mkdir -p $prefix && kallisto quant \\
+            --threads ${task.cpus} \\
+            --index ${index} \\
+            ${gtf_input} \\
+            ${chromosomes_input} \\
+            ${single_end_params} \\
+            ${strandedness} \\
+            ${args} \\
+            -o $prefix \\
+            ${reads} 2> >(tee -a ${prefix}/kallisto_quant.log >&2)
+
+    cp ${prefix}/kallisto_quant.log ${prefix}.log
+    cp ${prefix}/run_info.json ${prefix}.run_info.json
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kallisto: \$(echo \$(kallisto version) | sed "s/kallisto, version //g" )
+    END_VERSIONS
+    """
+
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    mkdir -p $prefix
+    touch ${prefix}.log
+    touch ${prefix}.run_info.json
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kallisto: \$(echo \$(kallisto version) | sed "s/kallisto, version //g" )
+    END_VERSIONS
+    """
+}