Hello Humann

conf/test.config

@@ -15,8 +15,8 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
+    max_cpus   = 4
+    max_memory = '16.GB'
     max_time   = '6.h'
 
     // Input data
@@ -25,6 +25,9 @@ params {
     run_kneaddata           = true
     kneaddata_db_version    = 'human_genome'
     run_metaphlan           = true
-    metaphlan_db_version    = 'mpa_vJan21_TOY_CHOCOPhlAnSGB_202103'
+    metaphlan_db_version    = 'mpa_vOct22_CHOCOPhlAnSGB_202212'
+    run_humann              = true
+    chocophlan_db_version   = 'DEMO'
+    uniref_db_version       = 'DEMO_diamond'
 
 }

modules/local/humann/humann/environment.yml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::humann=3.8

modules/local/humann/humann/main.nf

@@ -0,0 +1,58 @@
+process HUMANN_HUMANN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/humann:3.8--pyh7cba7a3_0':
+        'biocontainers/humann:3.8--pyh7cba7a3_0' }"
+
+    input:
+    tuple val(meta) , path(reads)
+    tuple val(meta2), path(metaphlan_profile)
+    path chocophlan_db
+    path uniref_db
+
+    output:
+    tuple val(meta), path("*_genefamilies.tsv") , emit: genefamilies
+    tuple val(meta), path("*_pathabundance.tsv"), emit: pathabundance
+    tuple val(meta), path("*_pathcoverage.tsv") , emit: pathcoverage
+    tuple val(meta), path("*.log")              , emit: log
+    path "versions.yml"                         , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_data  = !meta.single_end ? "--input ${reads[0]} --input ${reads[1]}" : "--input $reads"
+    """
+    humann \\
+        ${input_data} \\
+        --output ./ \\
+        --threads ${task.cpus} \\
+        --taxonomic-profile ${metaphlan_profile} \\
+        --nucleotide-database ${chocophlan_db} \\
+        --protein-database ${uniref_db} \\
+        --o-log ${prefix}.log \\
+        ${args}
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        humann: \$(echo \$(humann --version 2>&1 | sed 's/^.*humann //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_genefamilies.tsv
+    touch ${prefix}_pathabundance.tsv
+    touch ${prefix}_pathcoverage.tsv
+    touch ${prefix}.log
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        humann: \$(echo \$(humann --version 2>&1 | sed 's/^.*humann //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/local/humann/humann/nextflow.config

@@ -0,0 +1,27 @@
+process {
+    withName: HUMANN_HUMANN {
+        publishDir = [
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*_genefamilies.tsv'
+            ],
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*_pathabundance.tsv'
+            ],
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*_pathcoverage.tsv'
+            ],
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ],
+        ]
+        ext.args = params.humann_options ? params.humann_options : ""
+    }
+}

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

@@ -0,0 +1,115 @@
+nextflow_process {
+
+    name "Test Process HUMANN_HUMANN"
+    script "../main.nf"
+    process "HUMANN_HUMANN"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "humann"
+    tag "humann/humann"
+
+    setup {
+        run("HUMANN_DOWNLOADCHOCOPHLANDB") {
+            script "../../downloadchocophlandb/main.nf"
+            process {
+                """
+                input[0] = 'TODO - some chocophlan db version - or maybe skip this setup and build in a mini test db'
+                """
+            }
+        }
+
+        run("HUMANN_DOWNLOADUNIREFDB") {
+            script "../../downloadunirefdb/main.nf"
+            process {
+                """
+                input[0] = 'TODO - some uniref db version - or maybe skip this setup and build in a mini test db'
+                """
+            }
+        }
+    }
+
+    test("kneaded fastq.gz") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of(
+                    [
+                        [ id: 'test' ],
+                        [
+                            file(params.modules_testdata_base_path + "TODO_some_kneaded_1.fastq.gz", checkIfExists: true),
+                            file(params.modules_testdata_base_path + "TODO_some_kneaded_2.fastq.gz", checkIfExists: true)
+                        ]
+                    ]
+                )
+                input[1] = Channel.of(
+                    [
+                        [id: 'test'],
+                        [
+                            file(params.modules_testdata_base_path + "TODO_some_metaphlan_profile.tsv", checkIfExists: true)
+                        ]
+                    ]
+                )
+                input[2] = HUMANN_DOWNLOADCHOCOPHLANDB.out.chocophlan_db
+                input[3] = HUMANN_DOWNLOADUNIREFDB.out.uniref_db
+                """
+            }
+        }
+
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                    process.out.genefamilies
+                    process.out.pathabundance
+                    process.out.pathcoverage,
+                    process.out.versions
+                    ).match()
+                },
+                { assert path(process.out.log[0][1]).text.contains("TODO a line indicates its running and gives a version, hopefully?") }
+            )
+        }
+    }
+
+    test("kneaded fastq.gz - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of(
+                    [
+                        [ id: 'test' ],
+                        [
+                            file(params.modules_testdata_base_path + "TODO_some_kneaded_1.fastq.gz", checkIfExists: true),
+                            file(params.modules_testdata_base_path + "TODO_some_kneaded_2.fastq.gz", checkIfExists: true)
+                        ]
+                    ]
+                )
+                input[1] = Channel.of(
+                    [
+                        [id: 'test'],
+                        [
+                            file(params.modules_testdata_base_path + "TODO_some_metaphlan_profile.tsv", checkIfExists: true)
+                        ]
+                    ]
+                )
+                input[2] = HUMANN_DOWNLOADCHOCOPHLANDB.out.chocophlan_db
+                input[3] = HUMANN_DOWNLOADUNIREFDB.out.uniref_db
+                """
+            }
+        }
+
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/local/humann/humann/tests/nextflow.config

@@ -0,0 +1,27 @@
+process {
+    withName: HUMANN_HUMANN {
+        publishDir = [
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*_genefamilies.tsv'
+            ],
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*_pathabundance.tsv'
+            ],
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*_pathcoverage.tsv'
+            ],
+            [
+                path: { "${params.outdir}/humann/humann" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ],
+        ]
+        ext.args = params.humann_options ? params.humann_options : ""
+    }
+}

modules/local/humann/join/environment.yml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::humann=3.8

modules/local/humann/join/main.nf

@@ -0,0 +1,39 @@
+process HUMANN_JOIN {
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/humann:3.8--pyh7cba7a3_0':
+        'biocontainers/humann:3.8--pyh7cba7a3_0' }"
+
+    input:
+    tuple val(meta), path(input)
+    val file_name_pattern
+
+    output:
+    path("*_joined.tsv")   , emit: joined
+    path "versions.yml"    , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    humann_join_tables \\
+        --input . \\
+        --output ${file_name_pattern}_joined.tsv \\
+        --file_name $file_name_pattern \\
+        ${args}
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        humann: \$(echo \$(humann --version 2>&1 | sed 's/^.*humann //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch ${file_name_pattern}_joined.tsv
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        humann: \$(echo \$(humann --version 2>&1 | sed 's/^.*humann //; s/Using.*\$//' ))
+    END_VERSIONS
+    """
+}

modules/local/humann/join/nextflow.config

@@ -0,0 +1,12 @@
+process {
+    withName: HUMANN_JOIN {
+        publishDir = [
+            [
+                path: { "${params.outdir}/humann/results" },
+                mode: params.publish_dir_mode,
+                pattern: '*_joined.tsv.gz'
+            ]
+        ]
+        ext.args = params.humann_options ? params.humann_options : ""
+    }
+}

modules/local/humann/join/tests/main.nf.test

@@ -0,0 +1,54 @@
+nextflow_process {
+
+    name "Test Process HUMANN_JOIN"
+    script "../main.nf"
+    process "HUMANN_JOIN"
+    config "./nextflow.config"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "humann"
+    tag "humann/join"
+
+    test("humann/join") {
+        when {
+            process {
+                """
+                input[0] = "genefamilies"
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert process.success },
+                { assert snapshot(
+                    process.out.joined
+                    process.out.versions
+                    ).match()
+                },
+                { assert path(process.out.log[0][1]).text.contains("TODO a line indicates its running and gives a version, hopefully?") }
+            )
+        }
+    }
+
+    test("humann/join - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = "genefamilies"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/local/humann/join/tests/nextflow.config

@@ -0,0 +1,12 @@
+process {
+    withName: HUMANN_JOIN {
+        publishDir = [
+            [
+                path: { "${params.outdir}/humann/results" },
+                mode: params.publish_dir_mode,
+                pattern: '*_joined.tsv.gz'
+            ]
+        ]
+        ext.args = params.humann_options ? params.humann_options : ""
+    }
+}

modules/local/humann/regroup/environment.yml

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::humann=3.8