diff --git a/conf/modules.config b/conf/modules.config index 3e96760..b858ec3 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -273,7 +273,7 @@ process { ] } - withName: MEGAN_RMA2INFO { + withName: 'NFCORE_TAXPROFILER:TAXPROFILER:PROFILING:MEGAN_RMA2INFO' { ext.args = "-c2c Taxonomy" ext.prefix = { "${meta.id}" } publishDir = [ @@ -293,7 +293,32 @@ process { ] } + withName: KRONA_CLEANUP { + ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" } + publishDir = [ + path: { "${params.outdir}/krona" }, + mode: params.publish_dir_mode, + pattern: '*.{html}' + ] + } + withName: KRONA_KTIMPORTTEXT { + ext.prefix = { "${meta.tool}-${meta.id}" } + publishDir = [ + path: { "${params.outdir}/krona" }, + mode: params.publish_dir_mode, + pattern: '*.{html}' + ] + } + + withName: 'NFCORE_TAXPROFILER:TAXPROFILER:VISUALIZATION_KRONA:MEGAN_RMA2INFO' { + ext.args = { "--read2class Taxonomy" } + ext.prefix = { "${meta.id}-${meta.db_name}" } + } + + withName: KRONA_KTIMPORTTAXONOMY { + ext.args = "-i" + ext.prefix = { "${meta.tool}-${meta.id}" } publishDir = [ path: { "${params.outdir}/krona" }, mode: params.publish_dir_mode, diff --git a/conf/test.config b/conf/test.config index 564c0e8..6aaf058 100644 --- a/conf/test.config +++ b/conf/test.config @@ -39,6 +39,7 @@ params { run_diamond = true run_motus = false run_krona = true + krona_taxonomy_directory = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab' malt_save_reads = true kraken2_save_reads = true centrifuge_save_reads = true diff --git a/modules.json b/modules.json index 2524d25..1d40748 100644 --- a/modules.json +++ b/modules.json @@ -39,6 +39,9 @@ "filtlong": { "git_sha": "089f761f0bf79c4a486f1df9b6205f650196a2c1" }, + "gunzip": { + "git_sha": "9aadd9a6d3f5964476582319b3a1c54a3e3fe7c9" + }, "kaiju/kaiju": { "git_sha": "8856f127c58f6af479128be8b8df4d42e442ddbe" }, @@ -54,6 +57,9 @@ "krakentools/kreport2krona": { "git_sha": "8b2a473f586bed003e72d2b183acc43fc0ddc422" }, + "krona/ktimporttaxonomy": { + "git_sha": "0e9fd9370ad1845870b8a9c63fcc47d999a1739e" + }, "krona/ktimporttext": { "git_sha": "cdefbec66999c0b49d8bfeea9d6f9d19056635a2" }, diff --git a/modules/nf-core/modules/gunzip/main.nf b/modules/nf-core/modules/gunzip/main.nf new file mode 100644 index 0000000..61bf1af --- /dev/null +++ b/modules/nf-core/modules/gunzip/main.nf @@ -0,0 +1,34 @@ +process GUNZIP { + tag "$archive" + label 'process_low' + + conda (params.enable_conda ? "conda-forge::sed=4.7" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : + 'ubuntu:20.04' }" + + input: + tuple val(meta), path(archive) + + output: + tuple val(meta), path("$gunzip"), emit: gunzip + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + gunzip = archive.toString() - '.gz' + """ + gunzip \\ + -f \\ + $args \\ + $archive + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/gunzip/meta.yml b/modules/nf-core/modules/gunzip/meta.yml new file mode 100644 index 0000000..4d2ebc8 --- /dev/null +++ b/modules/nf-core/modules/gunzip/meta.yml @@ -0,0 +1,34 @@ +name: gunzip +description: Compresses and decompresses files. +keywords: + - gunzip + - compression +tools: + - gunzip: + description: | + gzip is a file format and a software application used for file compression and decompression. + documentation: https://www.gnu.org/software/gzip/manual/gzip.html + licence: ["GPL-3.0-or-later"] +input: + - meta: + type: map + description: | + Optional groovy Map containing meta information + e.g. [ id:'test', single_end:false ] + - archive: + type: file + description: File to be compressed/uncompressed + pattern: "*.*" +output: + - gunzip: + type: file + description: Compressed/uncompressed file + pattern: "*.*" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@joseespinosa" + - "@drpatelh" + - "@jfy133" diff --git a/modules/nf-core/modules/krona/ktimporttaxonomy/main.nf b/modules/nf-core/modules/krona/ktimporttaxonomy/main.nf new file mode 100644 index 0000000..9b03462 --- /dev/null +++ b/modules/nf-core/modules/krona/ktimporttaxonomy/main.nf @@ -0,0 +1,41 @@ +process KRONA_KTIMPORTTAXONOMY { + tag "${meta.id}" + label 'process_high' + + // WARN: Version information not provided by tool on CLI. Please update version string below when bumping container versions. + conda (params.enable_conda ? "bioconda::krona=2.8" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/krona:2.8--pl5262hdfd78af_2' : + 'quay.io/biocontainers/krona:2.8--pl5262hdfd78af_2' }" + + input: + tuple val(meta), path(report) + path taxonomy, stageAs: 'taxonomy.tab' + + output: + tuple val(meta), path ('*.html'), emit: html + 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 = '2.8' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions. + """ + TAXONOMY=\$(find -L . -name '*.tab' -exec dirname {} \\;) + echo \$TAXONOMY + + ktImportTaxonomy \\ + $args \\ + -o ${prefix}.html \\ + -tax \$TAXONOMY/ \\ + $report + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + krona: $VERSION + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/krona/ktimporttaxonomy/meta.yml b/modules/nf-core/modules/krona/ktimporttaxonomy/meta.yml new file mode 100644 index 0000000..0fd7d5f --- /dev/null +++ b/modules/nf-core/modules/krona/ktimporttaxonomy/meta.yml @@ -0,0 +1,48 @@ +name: krona_ktimporttaxonomy +description: KronaTools Import Taxonomy imports taxonomy classifications and produces an interactive Krona plot. +keywords: + - plot + - taxonomy + - interactive + - html + - visualisation + - krona chart +tools: + - krona: + description: Krona Tools is a set of scripts to create Krona charts from several Bioinformatics tools as well as from text and XML files. + homepage: https://github.com/marbl/Krona/wiki/KronaTools + documentation: http://manpages.ubuntu.com/manpages/impish/man1/ktImportTaxonomy.1.html + tool_dev_url: + doi: https://doi.org/10.1186/1471-2105-12-385 + licence: + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test'] + - database: + type: file + description: | + Path to a Krona taxonomy .tab file normally downloaded and generated by + krona/ktUpdateTaxonomy. Custom taxonomy files can have any name, but + must end in `.tab`. + pattern: "*tab" + - report: + type: file + description: "A tab-delimited file with taxonomy IDs and (optionally) query IDs, magnitudes, and scores. Query IDs are taken from column 1, taxonomy IDs from column 2, and scores from column 3. Lines beginning with # will be ignored." + pattern: "*.{tsv}" + +output: + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - html: + type: file + description: A html file containing an interactive krona plot. + pattern: "*.{html}" + +authors: + - "@mjakobs" diff --git a/nextflow.config b/nextflow.config index a5616e7..7160d0f 100644 --- a/nextflow.config +++ b/nextflow.config @@ -131,6 +131,7 @@ params { // krona run_krona = false + krona_taxonomy_directory = null } // Load base.config by default for all pipelines diff --git a/nextflow_schema.json b/nextflow_schema.json index e857ec8..4eec889 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -441,6 +441,10 @@ }, "run_krona": { "type": "boolean" + }, + "krona_taxonomy_directory": { + "type": "string", + "default": null } } } diff --git a/subworkflows/local/visualization_krona.nf b/subworkflows/local/visualization_krona.nf index c5ca97a..7a94fc6 100644 --- a/subworkflows/local/visualization_krona.nf +++ b/subworkflows/local/visualization_krona.nf @@ -2,10 +2,13 @@ // Create Krona visualizations // +include { MEGAN_RMA2INFO } from '../../modules/nf-core/modules/megan/rma2info/main' include { KAIJU_KAIJU2KRONA } from '../../modules/nf-core/modules/kaiju/kaiju2krona/main' include { KRAKENTOOLS_KREPORT2KRONA } from '../../modules/nf-core/modules/krakentools/kreport2krona/main' include { KRONA_CLEANUP } from '../../modules/local/krona_cleanup' include { KRONA_KTIMPORTTEXT } from '../../modules/nf-core/modules/krona/ktimporttext/main' +include { KRONA_KTIMPORTTAXONOMY } from '../../modules/nf-core/modules/krona/ktimporttaxonomy/main' +include { GUNZIP } from '../../modules/nf-core/modules/gunzip/main' workflow VISUALIZATION_KRONA { take: @@ -30,6 +33,7 @@ workflow VISUALIZATION_KRONA { ch_input_classifications = classifications .branch { kaiju: it[0]['tool'] == 'kaiju' + malt: it[0]['tool'] == 'malt' unknown: true } @@ -72,12 +76,29 @@ workflow VISUALIZATION_KRONA { Convert Krona text files into html Krona visualizations */ ch_krona_text_for_import = ch_cleaned_krona_text - .map{[[id: it[0]['db_name']], it[1]]} + .map{[[id: it[0]['db_name'], tool: it[0]['tool']], it[1]]} .groupTuple() + .dump(tag: "text") KRONA_KTIMPORTTEXT( ch_krona_text_for_import ) ch_krona_html = ch_krona_html.mix( KRONA_KTIMPORTTEXT.out.html ) ch_versions = ch_versions.mix( KRONA_KTIMPORTTEXT.out.versions.first() ) + /* + Convert MALT/MEGAN RMA2INFO files into html Krona visualisations + */ + if ( params.krona_taxonomy_directory ) { + MEGAN_RMA2INFO ( ch_input_classifications.malt, false ) + GUNZIP ( MEGAN_RMA2INFO.out.txt ) + ch_krona_taxonomy_for_input = GUNZIP.out.gunzip + .map{[[id: it[0]['db_name'], tool: it[0]['tool']], it[1]]} + .groupTuple() + .dump(tag: "taxonomy") + KRONA_KTIMPORTTAXONOMY ( ch_krona_taxonomy_for_input, file(params.krona_taxonomy_directory, checkExists: true) ) + ch_krona_html.mix( KRONA_KTIMPORTTAXONOMY.out.html ) + ch_versions = ch_versions.mix( MEGAN_RMA2INFO.out.versions.first() ) + ch_versions = ch_versions.mix( KRONA_KTIMPORTTAXONOMY.out.versions.first() ) + } + emit: html = ch_krona_html versions = ch_versions diff --git a/workflows/taxprofiler.nf b/workflows/taxprofiler.nf index 7eec13d..2037649 100644 --- a/workflows/taxprofiler.nf +++ b/workflows/taxprofiler.nf @@ -35,6 +35,8 @@ if (params.longread_hostremoval_index ) { ch_longread_reference_index = fi if (params.diamond_save_reads ) log.warn "[nf-core/taxprofiler] DIAMOND only allows output of a single format. As --diamond_save_reads supplied, only aligned reads in SAM format will be produced, no taxonomic profiles will be available." +if (params.run_malt && params.run_krona && !params.krona_taxonomy_directory) log.warn "[nf-core/taxprofiler] Krona can only be run on MALT output if path to Krona taxonomy database supplied to --krona_taxonomy_directory. Krona will not be executed in this run for MALT." + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CONFIG FILES