From bfe944536ecddc3a7a14ca83e740e417f372fd67 Mon Sep 17 00:00:00 2001 From: Tyler Chafin Date: Mon, 2 Dec 2024 13:45:10 +0000 Subject: [PATCH] busco updated/patched/tested --- conf/modules.config | 6 +- modules.json | 56 +- .../{busco.diff => busco/busco-busco.diff} | 8 +- .../nf-core/busco/{ => busco}/environment.yml | 4 +- modules/nf-core/busco/{ => busco}/main.nf | 33 +- modules/nf-core/busco/busco/meta.yml | 152 +++++ .../nf-core/busco/busco/tests/main.nf.test | 415 ++++++++++++ .../busco/busco/tests/main.nf.test.snap | 230 +++++++ .../busco/tests/nextflow.augustus.config | 5 + .../nf-core/busco/busco/tests/nextflow.config | 5 + .../busco/busco/tests/nextflow.metaeuk.config | 5 + .../nf-core/busco/busco/tests/old_test.yml | 624 ++++++++++++++++++ modules/nf-core/busco/busco/tests/tags.yml | 2 + modules/nf-core/busco/meta.yml | 96 --- subworkflows/local/genome_statistics.nf | 12 +- 15 files changed, 1515 insertions(+), 138 deletions(-) rename modules/nf-core/busco/{busco.diff => busco/busco-busco.diff} (87%) rename modules/nf-core/busco/{ => busco}/environment.yml (50%) rename modules/nf-core/busco/{ => busco}/main.nf (80%) create mode 100644 modules/nf-core/busco/busco/meta.yml create mode 100644 modules/nf-core/busco/busco/tests/main.nf.test create mode 100644 modules/nf-core/busco/busco/tests/main.nf.test.snap create mode 100644 modules/nf-core/busco/busco/tests/nextflow.augustus.config create mode 100644 modules/nf-core/busco/busco/tests/nextflow.config create mode 100644 modules/nf-core/busco/busco/tests/nextflow.metaeuk.config create mode 100644 modules/nf-core/busco/busco/tests/old_test.yml create mode 100644 modules/nf-core/busco/busco/tests/tags.yml delete mode 100644 modules/nf-core/busco/meta.yml diff --git a/conf/modules.config b/conf/modules.config index ec011e2f..a521d896 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -49,14 +49,14 @@ process { ] } - withName: BUSCO { + withName: "BUSCO|BUSCO_BUSCO" { // Obey "use_work_dir_as_temp", except for large genomes scratch = { !params.use_work_dir_as_temp || (meta.genome_size < 2000000000) } ext.args = { 'test' in workflow.profile.tokenize(',') ? // Additional configuration to speed processes up during testing. // Note: BUSCO *must* see the double-quotes around the parameters - '--mode genome --tar --metaeuk_parameters \'"-s=2"\' --metaeuk_rerun_parameters \'"-s=2"\'' - : '--mode genome --tar' } + '--mode genome --tar --metaeuk --metaeuk_parameters \'"-s=2"\' --metaeuk_rerun_parameters \'"-s=2"\'' + : '--mode genome --tar --metaeuk ' } } withName: "RESTRUCTUREBUSCODIR" { diff --git a/modules.json b/modules.json index 96922861..093dc1b9 100644 --- a/modules.json +++ b/modules.json @@ -8,68 +8,92 @@ "bedtools/bamtobed": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, - "busco": { + "busco/busco": { "branch": "master", - "git_sha": "e3126f437c336c826f242842fe51769cfce0ec2d", - "installed_by": ["modules"], - "patch": "modules/nf-core/busco/busco.diff" + "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", + "installed_by": [ + "modules" + ], + "patch": "modules/nf-core/busco/busco/busco-busco.diff" }, "cooler/cload": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cooler/dump": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cooler/zoomify": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "custom/dumpsoftwareversions": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "fastk/fastk": { "branch": "master", "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", - "installed_by": ["modules"], + "installed_by": [ + "modules" + ], "patch": "modules/nf-core/fastk/fastk/fastk-fastk.diff" }, "gnu/sort": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "gunzip": { "branch": "master", "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "merquryfk/merquryfk": { "branch": "master", "git_sha": "0f8a77ff00e65eaeebc509b8156eaa983192474b", - "installed_by": ["modules"], + "installed_by": [ + "modules" + ], "patch": "modules/nf-core/merquryfk/merquryfk/merquryfk-merquryfk.diff" }, "multiqc": { "branch": "master", "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "samtools/view": { "branch": "master", "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] } } } } } -} +} \ No newline at end of file diff --git a/modules/nf-core/busco/busco.diff b/modules/nf-core/busco/busco/busco-busco.diff similarity index 87% rename from modules/nf-core/busco/busco.diff rename to modules/nf-core/busco/busco/busco-busco.diff index 775788fb..1317574a 100644 --- a/modules/nf-core/busco/busco.diff +++ b/modules/nf-core/busco/busco/busco-busco.diff @@ -1,8 +1,8 @@ -Changes in module 'nf-core/busco' ---- modules/nf-core/busco/main.nf -+++ modules/nf-core/busco/main.nf +Changes in module 'nf-core/busco/busco' +--- modules/nf-core/busco/busco/main.nf ++++ modules/nf-core/busco/busco/main.nf @@ -1,6 +1,5 @@ - process BUSCO { + process BUSCO_BUSCO { - tag "$meta.id" - label 'process_medium' + tag "${meta.id}_${lineage}" diff --git a/modules/nf-core/busco/environment.yml b/modules/nf-core/busco/busco/environment.yml similarity index 50% rename from modules/nf-core/busco/environment.yml rename to modules/nf-core/busco/busco/environment.yml index f872d057..5b918b45 100644 --- a/modules/nf-core/busco/environment.yml +++ b/modules/nf-core/busco/busco/environment.yml @@ -1,7 +1,5 @@ -name: busco channels: - conda-forge - bioconda - - defaults dependencies: - - bioconda::busco=5.5.0 + - bioconda::busco=5.7.1 diff --git a/modules/nf-core/busco/main.nf b/modules/nf-core/busco/busco/main.nf similarity index 80% rename from modules/nf-core/busco/main.nf rename to modules/nf-core/busco/busco/main.nf index 83d8eacd..319f7235 100644 --- a/modules/nf-core/busco/main.nf +++ b/modules/nf-core/busco/busco/main.nf @@ -1,13 +1,13 @@ -process BUSCO { +process BUSCO_BUSCO { tag "${meta.id}_${lineage}" conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/busco:5.5.0--pyhdfd78af_0': - 'biocontainers/busco:5.5.0--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/busco:5.7.1--pyhdfd78af_0': + 'biocontainers/busco:5.7.1--pyhdfd78af_0' }" input: - tuple val(meta), path('tmp_input/*') + tuple val(meta), path(fasta, stageAs:'tmp_input/*') val mode // Required: One of genome, proteins, or transcriptome val lineage // Required: lineage to check against, "auto" enables --auto-lineage instead path busco_lineages_path // Recommended: path to busco lineages - downloads if not set @@ -15,13 +15,13 @@ process BUSCO { output: tuple val(meta), path("*-busco.batch_summary.txt") , emit: batch_summary - tuple val(meta), path("short_summary.*.txt") , emit: short_summaries_txt, optional: true - tuple val(meta), path("short_summary.*.json") , emit: short_summaries_json, optional: true - tuple val(meta), path("*-busco/*/run_*/full_table.tsv") , emit: full_table, optional: true - tuple val(meta), path("*-busco/*/run_*/missing_busco_list.tsv") , emit: missing_busco_list, optional: true - tuple val(meta), path("*-busco/*/run_*/single_copy_proteins.faa") , emit: single_copy_proteins, optional: true + tuple val(meta), path("short_summary.*.txt") , emit: short_summaries_txt , optional: true + tuple val(meta), path("short_summary.*.json") , emit: short_summaries_json , optional: true + tuple val(meta), path("*-busco/*/run_*/full_table.tsv") , emit: full_table , optional: true + tuple val(meta), path("*-busco/*/run_*/missing_busco_list.tsv") , emit: missing_busco_list , optional: true + tuple val(meta), path("*-busco/*/run_*/single_copy_proteins.faa") , emit: single_copy_proteins , optional: true tuple val(meta), path("*-busco/*/run_*/busco_sequences") , emit: seq_dir - tuple val(meta), path("*-busco/*/translated_proteins") , emit: translated_dir, optional: true + tuple val(meta), path("*-busco/*/translated_proteins") , emit: translated_dir , optional: true tuple val(meta), path("*-busco") , emit: busco_dir path "versions.yml" , emit: versions @@ -90,4 +90,17 @@ process BUSCO { busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' ) END_VERSIONS """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}-${lineage}" + def fasta_name = files(fasta).first().name - '.gz' + """ + touch ${prefix}-busco.batch_summary.txt + mkdir -p ${prefix}-busco/$fasta_name/run_${lineage}/busco_sequences + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' ) + END_VERSIONS + """ } diff --git a/modules/nf-core/busco/busco/meta.yml b/modules/nf-core/busco/busco/meta.yml new file mode 100644 index 00000000..7cb6d69c --- /dev/null +++ b/modules/nf-core/busco/busco/meta.yml @@ -0,0 +1,152 @@ +name: busco_busco +description: Benchmarking Universal Single Copy Orthologs +keywords: + - quality control + - genome + - transcriptome + - proteome +tools: + - busco: + description: BUSCO provides measures for quantitative assessment of genome assembly, + gene set, and transcriptome completeness based on evolutionarily informed expectations + of gene content from near-universal single-copy orthologs selected from OrthoDB. + homepage: https://busco.ezlab.org/ + documentation: https://busco.ezlab.org/busco_userguide.html + tool_dev_url: https://gitlab.com/ezlab/busco + doi: "10.1007/978-1-4939-9173-0_14" + licence: ["MIT"] + identifier: biotools:busco +input: + - - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - fasta: + type: file + description: Nucleic or amino acid sequence file in FASTA format. + pattern: "*.{fasta,fna,fa,fasta.gz,fna.gz,fa.gz}" + - - mode: + type: string + description: The mode to run Busco in. One of genome, proteins, or transcriptome + pattern: "{genome,proteins,transcriptome}" + - - lineage: + type: string + description: The BUSCO lineage to use, or "auto" to automatically select lineage + - - busco_lineages_path: + type: directory + description: Path to local BUSCO lineages directory. + - - config_file: + type: file + description: Path to BUSCO config file. +output: + - batch_summary: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco.batch_summary.txt": + type: file + description: Summary of all sequence files analyzed + pattern: "*-busco.batch_summary.txt" + - short_summaries_txt: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - short_summary.*.txt: + type: file + description: Short Busco summary in plain text format + pattern: "short_summary.*.txt" + - short_summaries_json: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - short_summary.*.json: + type: file + description: Short Busco summary in JSON format + pattern: "short_summary.*.json" + - full_table: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco/*/run_*/full_table.tsv": + type: file + description: Full BUSCO results table + pattern: "full_table.tsv" + - missing_busco_list: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco/*/run_*/missing_busco_list.tsv": + type: file + description: List of missing BUSCOs + pattern: "missing_busco_list.tsv" + - single_copy_proteins: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco/*/run_*/single_copy_proteins.faa": + type: file + description: Fasta file of single copy proteins (transcriptome mode) + pattern: "single_copy_proteins.faa" + - seq_dir: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco/*/run_*/busco_sequences": + type: directory + description: BUSCO sequence directory + pattern: "busco_sequences" + - translated_dir: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco/*/translated_proteins": + type: directory + description: Six frame translations of each transcript made by the transcriptome + mode + pattern: "translated_dir" + - busco_dir: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*-busco": + type: directory + description: BUSCO lineage specific output + pattern: "*-busco" + - versions: + - versions.yml: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@priyanka-surana" + - "@charles-plessy" + - "@mahesh-panchal" + - "@muffato" + - "@jvhagey" + - "@gallvp" +maintainers: + - "@priyanka-surana" + - "@charles-plessy" + - "@mahesh-panchal" + - "@muffato" + - "@jvhagey" + - "@gallvp" diff --git a/modules/nf-core/busco/busco/tests/main.nf.test b/modules/nf-core/busco/busco/tests/main.nf.test new file mode 100644 index 00000000..bb7b49a9 --- /dev/null +++ b/modules/nf-core/busco/busco/tests/main.nf.test @@ -0,0 +1,415 @@ +nextflow_process { + + name "Test Process BUSCO_BUSCO" + script "../main.nf" + process "BUSCO_BUSCO" + + tag "modules" + tag "modules_nfcore" + tag "busco" + tag "busco/busco" + + test("test_busco_genome_single_fasta") { + + config './nextflow.config' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true) + ] + input[1] = 'genome' + input[2] = 'bacteria_odb10' // Launch with 'auto' to use --auto-lineage, and specified lineages // 'auto' removed from test due to memory issues + input[3] = [] // Download busco lineage + input[4] = [] // No config + """ + } + } + + then { + assert process.success + + with(path(process.out.short_summaries_txt[0][1]).text) { + assert contains('BUSCO version') + assert contains('The lineage dataset is') + assert contains('BUSCO was run in mode') + assert contains('Complete BUSCOs') + assert contains('Missing BUSCOs') + assert contains('Dependencies and versions') + } + + with(path(process.out.short_summaries_json[0][1]).text) { + assert contains('one_line_summary') + assert contains('mode') + assert contains('dataset') + } + + assert snapshot( + process.out.batch_summary[0][1], + process.out.full_table[0][1], + process.out.missing_busco_list[0][1], + process.out.versions[0] + ).match() + + with(file(process.out.seq_dir[0][1]).listFiles().collect { it.name }) { + assert contains('single_copy_busco_sequences.tar.gz') + assert contains('multi_copy_busco_sequences.tar.gz') + assert contains('fragmented_busco_sequences.tar.gz') + } + + with(path("${process.out.busco_dir[0][1]}/logs/busco.log").text) { + assert contains('DEBUG:busco.run_BUSCO') + assert contains('Results from dataset') + assert contains('how to cite BUSCO') + } + + assert process.out.single_copy_proteins == [] + assert process.out.translated_dir == [] + } + } + + test("test_busco_genome_multi_fasta") { + + config './nextflow.config' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + [ + file(params.modules_testdata_base_path + 'genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/prokaryotes/candidatus_portiera_aleyrodidarum/genome/genome.fasta', checkIfExists: true) + ] + ] + input[1] = 'genome' + input[2] = 'bacteria_odb10' + input[3] = [] + input[4] = [] + """ + } + } + + then { + assert process.success + + with(path(process.out.short_summaries_txt[0][1][0]).text) { + assert contains('BUSCO version') + assert contains('The lineage dataset is') + assert contains('BUSCO was run in mode') + assert contains('Complete BUSCOs') + assert contains('Missing BUSCOs') + assert contains('Dependencies and versions') + } + + with(path(process.out.short_summaries_txt[0][1][1]).text) { + assert contains('BUSCO version') + assert contains('The lineage dataset is') + assert contains('BUSCO was run in mode') + assert contains('Complete BUSCOs') + assert contains('Missing BUSCOs') + assert contains('Dependencies and versions') + } + + with(path(process.out.short_summaries_json[0][1][0]).text) { + assert contains('one_line_summary') + assert contains('mode') + assert contains('dataset') + } + + with(path(process.out.short_summaries_json[0][1][1]).text) { + assert contains('one_line_summary') + assert contains('mode') + assert contains('dataset') + } + + assert snapshot( + process.out.batch_summary[0][1], + process.out.full_table[0][1], + process.out.missing_busco_list[0][1], + process.out.versions[0] + ).match() + + with(file(process.out.seq_dir[0][1][0]).listFiles().collect { it.name }) { + assert contains('single_copy_busco_sequences.tar.gz') + assert contains('multi_copy_busco_sequences.tar.gz') + assert contains('fragmented_busco_sequences.tar.gz') + } + + with(file(process.out.seq_dir[0][1][1]).listFiles().collect { it.name }) { + assert contains('single_copy_busco_sequences.tar.gz') + assert contains('multi_copy_busco_sequences.tar.gz') + assert contains('fragmented_busco_sequences.tar.gz') + } + + with(path("${process.out.busco_dir[0][1]}/logs/busco.log").text) { + assert contains('DEBUG:busco.run_BUSCO') + assert contains('Results from dataset') + assert contains('how to cite BUSCO') + } + + assert process.out.single_copy_proteins == [] + assert process.out.translated_dir == [] + } + + } + + test("test_busco_eukaryote_metaeuk") { + + config './nextflow.metaeuk.config' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + ] + input[1] = 'genome' + input[2] = 'eukaryota_odb10' + input[3] = [] + input[4] = [] + """ + } + } + + then { + assert process.success + + with(path(process.out.short_summaries_txt[0][1]).text) { + assert contains('BUSCO version') + assert contains('The lineage dataset is') + assert contains('BUSCO was run in mode') + assert contains('Complete BUSCOs') + assert contains('Missing BUSCOs') + assert contains('Dependencies and versions') + } + + with(path(process.out.short_summaries_json[0][1]).text) { + assert contains('one_line_summary') + assert contains('mode') + assert contains('dataset') + } + + assert snapshot( + process.out.batch_summary[0][1], + process.out.full_table[0][1], + process.out.missing_busco_list[0][1], + process.out.versions[0] + ).match() + + with(file(process.out.seq_dir[0][1]).listFiles().collect { it.name }) { + assert contains('single_copy_busco_sequences.tar.gz') + assert contains('multi_copy_busco_sequences.tar.gz') + assert contains('fragmented_busco_sequences.tar.gz') + } + + with(path("${process.out.busco_dir[0][1]}/logs/busco.log").text) { + assert contains('DEBUG:busco.run_BUSCO') + assert contains('Results from dataset') + assert contains('how to cite BUSCO') + + } + + assert process.out.single_copy_proteins == [] + assert process.out.translated_dir == [] + } + + } + + test("test_busco_eukaryote_augustus") { + + config './nextflow.augustus.config' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + ] + input[1] = 'genome' + input[2] = 'eukaryota_odb10' + input[3] = [] + input[4] = [] + """ + } + } + + then { + assert process.success + + assert snapshot( + process.out.batch_summary[0][1], + process.out.versions[0] + ).match() + + with(path("${process.out.busco_dir[0][1]}/logs/busco.log").text) { + assert contains('DEBUG:busco.run_BUSCO') + assert contains('Augustus did not recognize any genes') + + } + + assert process.out.short_summaries_json == [] + assert process.out.short_summaries_txt == [] + assert process.out.missing_busco_list == [] + assert process.out.full_table == [] + assert process.out.single_copy_proteins == [] + assert process.out.translated_dir == [] + } + + } + + test("test_busco_protein") { + + config './nextflow.config' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/prokaryotes/candidatus_portiera_aleyrodidarum/genome/proteome.fasta', checkIfExists: true) + ] + input[1] = 'proteins' + input[2] = 'bacteria_odb10' + input[3] = [] + input[4] = [] + """ + } + } + + then { + assert process.success + + with(path(process.out.short_summaries_txt[0][1]).text) { + assert contains('BUSCO version') + assert contains('The lineage dataset is') + assert contains('BUSCO was run in mode') + assert contains('Complete BUSCOs') + assert contains('Missing BUSCOs') + assert contains('Dependencies and versions') + } + + with(path(process.out.short_summaries_json[0][1]).text) { + assert contains('one_line_summary') + assert contains('mode') + assert contains('dataset') + } + + assert snapshot( + process.out.batch_summary[0][1], + process.out.full_table[0][1], + process.out.missing_busco_list[0][1], + process.out.versions[0] + ).match() + + with(file(process.out.seq_dir[0][1]).listFiles().collect { it.name }) { + assert contains('single_copy_busco_sequences.tar.gz') + assert contains('multi_copy_busco_sequences.tar.gz') + assert contains('fragmented_busco_sequences.tar.gz') + } + + with(path("${process.out.busco_dir[0][1]}/logs/busco.log").text) { + assert contains('DEBUG:busco.run_BUSCO') + assert contains('Results from dataset') + assert contains('how to cite BUSCO') + } + + assert process.out.single_copy_proteins == [] + assert process.out.translated_dir == [] + } + + } + + test("test_busco_transcriptome") { + + config './nextflow.config' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/prokaryotes/bacteroides_fragilis/illumina/fasta/test1.contigs.fa.gz', checkIfExists: true) + ] + input[1] = 'transcriptome' + input[2] = 'bacteria_odb10' + input[3] = [] + input[4] = [] + """ + } + } + + then { + assert process.success + + with(path(process.out.short_summaries_txt[0][1]).text) { + assert contains('BUSCO version') + assert contains('The lineage dataset is') + assert contains('BUSCO was run in mode') + assert contains('Complete BUSCOs') + assert contains('Missing BUSCOs') + assert contains('Dependencies and versions') + } + + with(path(process.out.short_summaries_json[0][1]).text) { + assert contains('one_line_summary') + assert contains('mode') + assert contains('dataset') + } + + assert snapshot( + process.out.batch_summary[0][1], + process.out.full_table[0][1], + process.out.missing_busco_list[0][1], + process.out.translated_dir[0][1], + process.out.single_copy_proteins[0][1], + process.out.versions[0] + ).match() + + with(file(process.out.seq_dir[0][1]).listFiles().collect { it.name }) { + assert contains('single_copy_busco_sequences.tar.gz') + assert contains('multi_copy_busco_sequences.tar.gz') + assert contains('fragmented_busco_sequences.tar.gz') + } + + with(path("${process.out.busco_dir[0][1]}/logs/busco.log").text) { + assert contains('DEBUG:busco.run_BUSCO') + assert contains('Results from dataset') + assert contains('how to cite BUSCO') + } + } + + } + + test("minimal-stub") { + + options '-stub' + + when { + process { + """ + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true) + ] + input[1] = 'genome' + input[2] = 'bacteria_odb10' + input[3] = [] + input[4] = [] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } + +} diff --git a/modules/nf-core/busco/busco/tests/main.nf.test.snap b/modules/nf-core/busco/busco/tests/main.nf.test.snap new file mode 100644 index 00000000..1b6411bc --- /dev/null +++ b/modules/nf-core/busco/busco/tests/main.nf.test.snap @@ -0,0 +1,230 @@ +{ + "minimal-stub": { + "content": [ + { + "0": [ + [ + { + "id": "test" + }, + "test-bacteria_odb10-busco.batch_summary.txt:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "1": [ + + ], + "2": [ + + ], + "3": [ + + ], + "4": [ + + ], + "5": [ + + ], + "6": [ + [ + { + "id": "test" + }, + [ + + ] + ] + ], + "7": [ + + ], + "8": [ + [ + { + "id": "test" + }, + [ + [ + [ + [ + + ] + ] + ] + ] + ] + ], + "9": [ + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "batch_summary": [ + [ + { + "id": "test" + }, + "test-bacteria_odb10-busco.batch_summary.txt:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "busco_dir": [ + [ + { + "id": "test" + }, + [ + [ + [ + [ + + ] + ] + ] + ] + ] + ], + "full_table": [ + + ], + "missing_busco_list": [ + + ], + "seq_dir": [ + [ + { + "id": "test" + }, + [ + + ] + ] + ], + "short_summaries_json": [ + + ], + "short_summaries_txt": [ + + ], + "single_copy_proteins": [ + + ], + "translated_dir": [ + + ], + "versions": [ + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:28:04.451297" + }, + "test_busco_eukaryote_augustus": { + "content": [ + "test-eukaryota_odb10-busco.batch_summary.txt:md5,3ea3bdc423a461dae514d816bdc61c89", + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:26:36.974986" + }, + "test_busco_genome_single_fasta": { + "content": [ + "test-bacteria_odb10-busco.batch_summary.txt:md5,21b3fb771cf36be917cc451540d999be", + "full_table.tsv:md5,638fe7590f442c57361554dae330eca1", + "missing_busco_list.tsv:md5,1530af4fe7673a6d001349537bcd410a", + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:22:45.07816" + }, + "test_busco_genome_multi_fasta": { + "content": [ + "test-bacteria_odb10-busco.batch_summary.txt:md5,fcd3c208913e8abda3d6742c43fec5fa", + [ + "full_table.tsv:md5,c657edcc7d0de0175869717551df6e83", + "full_table.tsv:md5,638fe7590f442c57361554dae330eca1" + ], + [ + "missing_busco_list.tsv:md5,aceb66e347a353cb7fca8e2a725f9112", + "missing_busco_list.tsv:md5,1530af4fe7673a6d001349537bcd410a" + ], + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:23:50.255602" + }, + "test_busco_eukaryote_metaeuk": { + "content": [ + "test-eukaryota_odb10-busco.batch_summary.txt:md5,ff6d8277e452a83ce9456bbee666feb6", + "full_table.tsv:md5,92b1b1d5cb5ea0e2093d16f00187e8c7", + "missing_busco_list.tsv:md5,0352e563de290bf804c708323c35a9e3", + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:25:38.159041" + }, + "test_busco_transcriptome": { + "content": [ + "test-bacteria_odb10-busco.batch_summary.txt:md5,8734b3f379c4c0928e5dd4ea1873dc64", + "full_table.tsv:md5,1b2ce808fdafa744c56b5f781551272d", + "missing_busco_list.tsv:md5,a6931b6470262b997b8b99ea0f1d14a4", + [ + "1024388at2.faa:md5,797d603d262a6595a112e25b73e878b0", + "1054741at2.faa:md5,cd4b928cba6b19b4437746ba507e7195", + "1093223at2.faa:md5,df9549708e5ffcfaee6a74dd70a0e5dc", + "1151822at2.faa:md5,12726afc1cdc40c13392e1596e93df3a", + "143460at2.faa:md5,d887431fd988a5556a523440f02d9594", + "1491686at2.faa:md5,d03362d19979b27306c192f1c74a84e5", + "1504821at2.faa:md5,4f5f6e5c57bac0092c1d85ded73d7e67", + "1574817at2.faa:md5,1153e55998c2929eacad2aed7d08d248", + "1592033at2.faa:md5,bb7a59e5f3a57ba12d10dabf4c77ab57", + "1623045at2.faa:md5,8fe38155feb1802beb97ef7714837bf5", + "1661836at2.faa:md5,6c6d592c2fbb0d7a4e5e1f47a15644f0", + "1674344at2.faa:md5,bb41b44e53565a54cadf0b780532fe08", + "1698718at2.faa:md5,f233860000028eb00329aa85236c71e5", + "1990650at2.faa:md5,34a2d29c5f8b6253159ddb7a43fa1829", + "223233at2.faa:md5,dec6705c7846c989296e73942f953cbc", + "402899at2.faa:md5,acc0f271f9a586d2ce1ee41669b22999", + "505485at2.faa:md5,aa0391f8fa5d9bd19b30d844d5a99845", + "665824at2.faa:md5,47f8ad43b6a6078206feb48c2e552793", + "776861at2.faa:md5,f8b90c13f7c6be828dea3bb920195e3d", + "874197at2.faa:md5,8d22a35a768debe6f376fc695d233a69", + "932854at2.faa:md5,2eff2de1ab83b22f3234a529a44e22bb", + "95696at2.faa:md5,247bfd1aef432f7b5456307768e9149c" + ], + "single_copy_proteins.faa:md5,73e2c5d6a9b0f01f2deea3cc5f21b764", + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:27:53.992893" + }, + "test_busco_protein": { + "content": [ + "test-bacteria_odb10-busco.batch_summary.txt:md5,f5a782378f9f94a748aa907381fdef91", + "full_table.tsv:md5,812ab6a0496fccab774643cf40c4f2a8", + "missing_busco_list.tsv:md5,aceb66e347a353cb7fca8e2a725f9112", + "versions.yml:md5,3fc94714b95c2dc15399a4229d9dd1d9" + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-05-03T13:27:12.724862" + } +} \ No newline at end of file diff --git a/modules/nf-core/busco/busco/tests/nextflow.augustus.config b/modules/nf-core/busco/busco/tests/nextflow.augustus.config new file mode 100644 index 00000000..84daa69d --- /dev/null +++ b/modules/nf-core/busco/busco/tests/nextflow.augustus.config @@ -0,0 +1,5 @@ +process { + withName: 'BUSCO_BUSCO' { + ext.args = '--tar --augustus' + } +} diff --git a/modules/nf-core/busco/busco/tests/nextflow.config b/modules/nf-core/busco/busco/tests/nextflow.config new file mode 100644 index 00000000..1ec3fec0 --- /dev/null +++ b/modules/nf-core/busco/busco/tests/nextflow.config @@ -0,0 +1,5 @@ +process { + withName: 'BUSCO_BUSCO' { + ext.args = '--tar' + } +} diff --git a/modules/nf-core/busco/busco/tests/nextflow.metaeuk.config b/modules/nf-core/busco/busco/tests/nextflow.metaeuk.config new file mode 100644 index 00000000..c1418445 --- /dev/null +++ b/modules/nf-core/busco/busco/tests/nextflow.metaeuk.config @@ -0,0 +1,5 @@ +process { + withName: 'BUSCO_BUSCO' { + ext.args = '--tar --metaeuk' + } +} diff --git a/modules/nf-core/busco/busco/tests/old_test.yml b/modules/nf-core/busco/busco/tests/old_test.yml new file mode 100644 index 00000000..75177f5d --- /dev/null +++ b/modules/nf-core/busco/busco/tests/old_test.yml @@ -0,0 +1,624 @@ +- name: busco test_busco_genome_single_fasta + command: nextflow run ./tests/modules/nf-core/busco -entry test_busco_genome_single_fasta -c ./tests/config/nextflow.config + tags: + - busco + files: + - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt + md5sum: bc2440f8a68d7fbf931ff911c1c3fdfa + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/bbtools_err.log + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/bbtools_out.log + md5sum: 9caf1a1434414c78562eb0bbb9c0e53f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/hmmsearch_err.log + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/hmmsearch_out.log + contains: + - "# hmmsearch :: search profile(s) against a sequence database" + - "# target sequence database:" + - "Internal pipeline statistics summary:" + - "[ok]" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/prodigal_err.log + md5sum: 538510cfc7483498210f01e53fe035ad + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/prodigal_out.log + md5sum: 61050b0706addc9498b2088a2d6efa9a + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/.checkpoint + contains: + - "Tool: prodigal" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/predicted.faa + md5sum: 836e9a80d33d8b89168f07ddc13ee991 + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/predicted.fna + md5sum: 20eeb75f86842e6e136f02bca8b73a9f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.faa + md5sum: 836e9a80d33d8b89168f07ddc13ee991 + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.fna + md5sum: 20eeb75f86842e6e136f02bca8b73a9f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_err.log + md5sum: 538510cfc7483498210f01e53fe035ad + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_out.log + md5sum: 61050b0706addc9498b2088a2d6efa9a + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/.bbtools_output/.checkpoint + contains: + - "Tool: bbtools" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/full_table.tsv + md5sum: c56edab1dc1522e993c25ae2b730799f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/hmmer_output.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/missing_busco_list.tsv + md5sum: b533ef30270f27160acce85a22d01bf5 + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "lineage_dataset" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/test-bacteria_odb10-busco/logs/busco.log + contains: + - "DEBUG:busco.run_BUSCO" + - "Results from dataset" + - "how to cite BUSCO" + - path: output/busco/versions.yml + +- name: busco test_busco_genome_multi_fasta + command: nextflow run ./tests/modules/nf-core/busco -entry test_busco_genome_multi_fasta -c ./tests/config/nextflow.config + tags: + - busco + files: + - path: output/busco/short_summary.specific.bacteria_odb10.genome.fasta.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.bacteria_odb10.genome.fasta.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.bacteria_odb10.genome.fna.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt + md5sum: 8c64c1a28b086ef2ee444f99cbed5f7d + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/logs/bbtools_err.log + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/logs/bbtools_out.log + md5sum: 8f047bdb33264d22a83920bc2c63f29a + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/logs/hmmsearch_err.log + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/logs/hmmsearch_out.log + contains: + - "# hmmsearch :: search profile(s) against a sequence database" + - "# target sequence database:" + - "Internal pipeline statistics summary:" + - "[ok]" + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/logs/prodigal_err.log + md5sum: c1fdc6977332f53dfe7f632733bb4585 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/logs/prodigal_out.log + md5sum: 50752acb1c5a20be886bfdfc06635bcb + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/.checkpoint + contains: + - "Tool: prodigal" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/predicted.faa + md5sum: 8166471fc5f08c82fd5643ab42327f9d + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/predicted.fna + md5sum: ddc508a18f60e7f3314534df50cdf8ca + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.faa + md5sum: 8166471fc5f08c82fd5643ab42327f9d + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.fna + md5sum: ddc508a18f60e7f3314534df50cdf8ca + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_err.log + md5sum: c1fdc6977332f53dfe7f632733bb4585 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_out.log + md5sum: 50752acb1c5a20be886bfdfc06635bcb + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_4.faa + md5sum: e56fd59c38248dc21ac94355dca98121 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_4.fna + md5sum: b365f84bf99c68357952e0b98ed7ce42 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_4_err.log + md5sum: e5f14d7925ba14a0f9850542f3739894 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_4_out.log + md5sum: d41971bfc1b621d4ffd2633bc47017ea + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/.bbtools_output/.checkpoint + contains: + - "Tool: bbtools" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/full_table.tsv + md5sum: c9651b88b10871abc260ee655898e828 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/hmmer_output.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/missing_busco_list.tsv + md5sum: 9939309df2da5419de88c32d1435c779 + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/test-bacteria_odb10-busco/genome.fasta/run_bacteria_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/bbtools_err.log + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/bbtools_out.log + md5sum: 9caf1a1434414c78562eb0bbb9c0e53f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/hmmsearch_err.log + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/hmmsearch_out.log + contains: + - "# hmmsearch :: search profile(s) against a sequence database" + - "# target sequence database:" + - "Internal pipeline statistics summary:" + - "[ok]" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/prodigal_err.log + md5sum: 538510cfc7483498210f01e53fe035ad + - path: output/busco/test-bacteria_odb10-busco/genome.fna/logs/prodigal_out.log + md5sum: 61050b0706addc9498b2088a2d6efa9a + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/.checkpoint + contains: + - "Tool: prodigal" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/predicted.faa + md5sum: 836e9a80d33d8b89168f07ddc13ee991 + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/predicted.fna + md5sum: 20eeb75f86842e6e136f02bca8b73a9f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.faa + md5sum: 836e9a80d33d8b89168f07ddc13ee991 + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11.fna + md5sum: 20eeb75f86842e6e136f02bca8b73a9f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_err.log + md5sum: 538510cfc7483498210f01e53fe035ad + - path: output/busco/test-bacteria_odb10-busco/genome.fna/prodigal_output/predicted_genes/tmp/prodigal_mode_single_code_11_out.log + md5sum: 61050b0706addc9498b2088a2d6efa9a + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/.bbtools_output/.checkpoint + contains: + - "Tool: bbtools" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/full_table.tsv + md5sum: c56edab1dc1522e993c25ae2b730799f + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/hmmer_output.tar.gz + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/missing_busco_list.tsv + md5sum: b533ef30270f27160acce85a22d01bf5 + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/test-bacteria_odb10-busco/genome.fna/run_bacteria_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/test-bacteria_odb10-busco/logs/busco.log + contains: + - "DEBUG:busco.run_BUSCO" + - "Results from dataset" + - "how to cite BUSCO" + - path: output/busco/versions.yml + +- name: busco test_busco_eukaryote_metaeuk + command: nextflow run ./tests/modules/nf-core/busco -entry test_busco_eukaryote_metaeuk -c ./tests/config/nextflow.config + tags: + - busco + files: + - path: output/busco/short_summary.specific.eukaryota_odb10.genome.fasta.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.eukaryota_odb10.genome.fasta.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/test-eukaryota_odb10-busco.batch_summary.txt + md5sum: ff6d8277e452a83ce9456bbee666feb6 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/bbtools_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/bbtools_out.log + md5sum: e63debaa653f18f7405d936050abc093 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/hmmsearch_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/hmmsearch_out.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run1_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run1_out.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run2_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run2_out.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/.bbtools_output/.checkpoint + contains: + - "Tool: bbtools" + - "Completed" + - "jobs" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/full_table.tsv + md5sum: bd880e90b9e5620a58943a3e0f9ff16b + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/hmmer_output.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/.checkpoint + contains: + - "Tool: metaeuk" + - "Completed" + - "jobs" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/combined_pred_proteins.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.codon.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.gff + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.headersMap.tsv + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/refseq_db_rerun.faa + md5sum: d80b8fa4cb5ed0d47d63d6aa93635bc2 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.codon.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.gff + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.headersMap.tsv + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/missing_busco_list.tsv + md5sum: 1e8e79c540fd2e69ba0d2659d9eb2988 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/test-eukaryota_odb10-busco/logs/busco.log + contains: + - "DEBUG:busco.run_BUSCO" + - "Results from dataset" + - "how to cite BUSCO" + - path: output/busco/versions.yml + +- name: busco test_busco_eukaryote_augustus + command: nextflow run ./tests/modules/nf-core/busco -entry test_busco_eukaryote_augustus -c ./tests/config/nextflow.config + tags: + - busco + files: + - path: output/busco/short_summary.specific.eukaryota_odb10.genome.fasta.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.eukaryota_odb10.genome.fasta.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/test-eukaryota_odb10-busco.batch_summary.txt + md5sum: ff6d8277e452a83ce9456bbee666feb6 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/bbtools_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/bbtools_out.log + md5sum: e63debaa653f18f7405d936050abc093 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/hmmsearch_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/hmmsearch_out.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run1_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run1_out.log + contains: + - "metaeuk" + - "easy-predict" + - "Compute score and coverage" + - "Time for processing:" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run2_err.log + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/logs/metaeuk_run2_out.log + contains: + - "metaeuk" + - "easy-predict" + - "Compute score and coverage" + - "Time for processing:" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/.bbtools_output/.checkpoint + contains: + - "Tool: bbtools" + - "Completed" + - "jobs" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/full_table.tsv + md5sum: bd880e90b9e5620a58943a3e0f9ff16b + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/hmmer_output.tar.gz + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/.checkpoint + contains: + - "Tool: metaeuk" + - "Completed" + - "jobs" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/combined_pred_proteins.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.codon.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.gff + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/initial_results/genome.fasta.headersMap.tsv + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/refseq_db_rerun.faa + md5sum: d80b8fa4cb5ed0d47d63d6aa93635bc2 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.codon.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.fas + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.gff + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/metaeuk_output/rerun_results/genome.fasta.headersMap.tsv + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/missing_busco_list.tsv + md5sum: 1e8e79c540fd2e69ba0d2659d9eb2988 + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/test-eukaryota_odb10-busco/genome.fasta/run_eukaryota_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/test-eukaryota_odb10-busco/logs/busco.log + contains: + - "DEBUG:busco.run_BUSCO" + - "Results from dataset" + - "how to cite BUSCO" + - path: output/busco/versions.yml + +- name: busco test_busco_protein + command: nextflow run ./tests/modules/nf-core/busco -entry test_busco_protein -c ./tests/config/nextflow.config + tags: + - busco + files: + - path: output/busco/short_summary.specific.bacteria_odb10.proteome.fasta.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.bacteria_odb10.proteome.fasta.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt + md5sum: 7a65e6cbb6c56a2ea4e739ae0aa3297d + - path: output/busco/test-bacteria_odb10-busco/logs/busco.log + contains: + - "DEBUG:busco.run_BUSCO" + - "Results from dataset" + - "how to cite BUSCO" + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/logs/hmmsearch_err.log + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/logs/hmmsearch_out.log + contains: + - "# hmmsearch :: search profile(s) against a sequence database" + - "# target sequence database:" + - "Internal pipeline statistics summary:" + - "[ok]" + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/full_table.tsv + md5sum: 0e34f1011cd83ea1d5d5103ec62b8922 + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/hmmer_output.tar.gz + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/missing_busco_list.tsv + md5sum: 9939309df2da5419de88c32d1435c779 + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/test-bacteria_odb10-busco/proteome.fasta/run_bacteria_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/versions.yml + +- name: busco test_busco_transcriptome + command: nextflow run ./tests/modules/nf-core/busco -entry test_busco_transcriptome -c ./tests/config/nextflow.config + tags: + - busco + files: + - path: output/busco/short_summary.specific.bacteria_odb10.test1.contigs.fa.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/short_summary.specific.bacteria_odb10.test1.contigs.fa.txt + contains: + - "BUSCO version" + - "The lineage dataset is" + - "BUSCO was run in mode" + - "Complete BUSCOs" + - "Missing BUSCOs" + - "Dependencies and versions" + - path: output/busco/test-bacteria_odb10-busco.batch_summary.txt + md5sum: 46118ecf60d1b87d22b96d80f4f03632 + - path: output/busco/test-bacteria_odb10-busco/logs/busco.log + contains: + - "DEBUG:busco.run_BUSCO" + - "Results from dataset" + - "how to cite BUSCO" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/.checkpoint + contains: + - "Tool: makeblastdb" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.ndb + md5sum: 3788c017fe5e6f0f58224e9cdd21822b + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.nhr + md5sum: 8ecd2ce392bb5e25ddbe1d85f879582e + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.nin + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.njs + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.not + md5sum: 0c340e376c7e85d19f82ec1a833e6a6e + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.nsq + md5sum: 532d5c0a7ea00fe95ca3c97cb3be6198 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.ntf + md5sum: de1250813f0c7affc6d12dac9d0fb6bb + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/blast_db/test1.contigs.fa.nto + md5sum: ff74bd41f9cc9b011c63a32c4f7693bf + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/logs/hmmsearch_err.log + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/logs/hmmsearch_out.log + contains: + - "# hmmsearch :: search profile(s) against a sequence database" + - "# target sequence database:" + - "Internal pipeline statistics summary:" + - "[ok]" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/logs/makeblastdb_err.log + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/logs/makeblastdb_out.log + contains: + - "Building a new DB" + - "Adding sequences from FASTA" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/logs/tblastn_err.log + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/logs/tblastn_out.log + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/.checkpoint + contains: + - "Tool: tblastn" + - "Completed" + - "jobs" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/coordinates.tsv + md5sum: cc30eed321944af293452bdbcfc24292 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_101.temp + md5sum: 73e9c65fc83fedc58f57f09b08f08238 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_119.temp + md5sum: 7fa4cc7955ec0cc36330a221c579b975 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_129.temp + md5sum: 6f1601c875d019e3f6f1f98ed8e988d4 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_138.temp + md5sum: 3f8e034686cd240c2330650d791bcae2 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_143.temp + md5sum: df3dfa8e9ba30ed70cf75b5e7abf2179 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_172.temp + md5sum: 7d463e0e6cf7169bc9077d8dc776dda1 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_178.temp + md5sum: 2288edf7fa4f88f51b4cf4d94086f77e + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_188.temp + md5sum: 029906abbad6d87fc57830dd548cac24 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_195.temp + md5sum: 4937f3b348774a31b1160a00297c29cc + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_210.temp + md5sum: afcb20ba4c466479d6b91c8c62251e1f + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_232.temp + md5sum: 2e1e823ce017345bd998191a39fa9924 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_268.temp + md5sum: 08c2d82c34ecffbe1c638b410349412e + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_29.temp + md5sum: cd9b63cf93524284781535c888313764 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_44.temp + md5sum: d1929b742b24ebe379bf4801ca882dca + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_58.temp + md5sum: 69215765b010c05336538cb322c900b3 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_72.temp + md5sum: 6feaa1cc3b0899a147ea9d466878f3e3 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_80.temp + md5sum: 13625eae14e860a96ce17cd4e37e9d01 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_81.temp + md5sum: e14b2484649b0dbc8926815c207b806d + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_93.temp + md5sum: 6902c93691df00e690faea914c71839e + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/sequences/k141_97.temp + md5sum: 0a0d9d38a83acbd5ad43c29cdf429988 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/blast_output/tblastn.tsv + contains: + - "TBLASTN" + - "BLAST processed" + - "queries" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/busco_sequences/fragmented_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/busco_sequences/multi_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/busco_sequences/single_copy_busco_sequences.tar.gz + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/full_table.tsv + md5sum: 24df25199e13c88bd892fc3e7b541ca0 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/hmmer_output.tar.gz + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/missing_busco_list.tsv + md5sum: e7232e2b8cca4fdfdd9e363b39ebbc81 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/short_summary.json + contains: + - "one_line_summary" + - "mode" + - "dataset" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/short_summary.txt + contains: + - "# BUSCO version is:" + - "Results:" + - "busco:" + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/run_bacteria_odb10/single_copy_proteins.faa + md5sum: e04b9465733577ae6e4bccb7aa01e720 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1024388at2.faa + md5sum: 7333c39a20258f20c7019ea0cd83157c + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1054741at2.faa + md5sum: ebb481e77a824685fbe04d8a2f3a0d7d + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1093223at2.faa + md5sum: 34621c7d499034e8f8e6b92fd4020a93 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1151822at2.faa + md5sum: aa89ca381c1c70c9c4e1380351ca7c2a + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/143460at2.faa + md5sum: f2e91d78b8dd3722840378789f29e8c8 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1491686at2.faa + md5sum: 73c25aef5c9cba7f4151804941b146ea + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1504821at2.faa + md5sum: cda556018d1f84ebe517e89f6fc107d0 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1574817at2.faa + md5sum: a9096c9fb8b25c78a72871ab0463acdc + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1592033at2.faa + md5sum: e463d25ce186c0cebfd749474f3a4c64 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1623045at2.faa + md5sum: f2cfd241590c6d8377286d6135480937 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1661836at2.faa + md5sum: 586569546fb9861502468e3d9ba2775c + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1674344at2.faa + md5sum: 24c658bee14ad84b062d81ad96642eb8 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1698718at2.faa + md5sum: 0b8e26ddf5149bbd8805be7af125208d + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/1990650at2.faa + md5sum: 159320712ee01fb2ccb31a25df44eead + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/223233at2.faa + md5sum: 812629c0b06ac3d18661c2ca78de0c08 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/402899at2.faa + md5sum: f7ff4e1591342d30b77392a2e84b57d9 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/505485at2.faa + md5sum: 7b34a24fc49c540d46fcf96ff5129564 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/665824at2.faa + md5sum: 4cff2df64f6bcaff8bc19c234c8bcccd + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/776861at2.faa + md5sum: 613af7a3fea30ea2bece66f603b9284a + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/874197at2.faa + md5sum: a7cd1b13c9ef91c7ef4e31614166f197 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/932854at2.faa + md5sum: fe313ffd5efdb0fed887a04fba352552 + - path: output/busco/test-bacteria_odb10-busco/test1.contigs.fa/translated_proteins/95696at2.faa + md5sum: 4e1f30a2fea4dfbf9bb7fae2700622a0 + - path: output/busco/versions.yml diff --git a/modules/nf-core/busco/busco/tests/tags.yml b/modules/nf-core/busco/busco/tests/tags.yml new file mode 100644 index 00000000..7c4d2835 --- /dev/null +++ b/modules/nf-core/busco/busco/tests/tags.yml @@ -0,0 +1,2 @@ +busco/busco: + - "modules/nf-core/busco/busco/**" diff --git a/modules/nf-core/busco/meta.yml b/modules/nf-core/busco/meta.yml deleted file mode 100644 index 90b30d4d..00000000 --- a/modules/nf-core/busco/meta.yml +++ /dev/null @@ -1,96 +0,0 @@ -name: busco -description: Benchmarking Universal Single Copy Orthologs -keywords: - - quality control - - genome - - transcriptome - - proteome -tools: - - busco: - description: BUSCO provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs selected from OrthoDB. - homepage: https://busco.ezlab.org/ - documentation: https://busco.ezlab.org/busco_userguide.html - tool_dev_url: https://gitlab.com/ezlab/busco - doi: "10.1007/978-1-4939-9173-0_14" - licence: ["MIT"] -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - fasta: - type: file - description: Nucleic or amino acid sequence file in FASTA format. - pattern: "*.{fasta,fna,fa,fasta.gz,fna.gz,fa.gz}" - - mode: - type: string - description: The mode to run Busco in. One of genome, proteins, or transcriptome - pattern: "{genome,proteins,transcriptome}" - - lineage: - type: string - description: The BUSCO lineage to use, or "auto" to automatically select lineage - - busco_lineages_path: - type: directory - description: Path to local BUSCO lineages directory. - - config_file: - type: file - description: Path to BUSCO config file. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - batch_summary: - type: file - description: Summary of all sequence files analyzed - pattern: "*-busco.batch_summary.txt" - - short_summaries_txt: - type: file - description: Short Busco summary in plain text format - pattern: "short_summary.*.txt" - - short_summaries_json: - type: file - description: Short Busco summary in JSON format - pattern: "short_summary.*.json" - - busco_dir: - type: directory - description: BUSCO lineage specific output - pattern: "*-busco" - - full_table: - type: file - description: Full BUSCO results table - pattern: "full_table.tsv" - - missing_busco_list: - type: file - description: List of missing BUSCOs - pattern: "missing_busco_list.tsv" - - single_copy_proteins: - type: file - description: Fasta file of single copy proteins (transcriptome mode) - pattern: "single_copy_proteins.faa" - - seq_dir: - type: directory - description: BUSCO sequence directory - pattern: "busco_sequences" - - translated_proteins: - type: directory - description: Six frame translations of each transcript made by the transcriptome mode - pattern: "translated_proteins" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@priyanka-surana" - - "@charles-plessy" - - "@mahesh-panchal" - - "@muffato" - - "@jvhagey" -maintainers: - - "@priyanka-surana" - - "@charles-plessy" - - "@mahesh-panchal" - - "@muffato" - - "@jvhagey" diff --git a/subworkflows/local/genome_statistics.nf b/subworkflows/local/genome_statistics.nf index 73a7e2ba..9ac06b94 100644 --- a/subworkflows/local/genome_statistics.nf +++ b/subworkflows/local/genome_statistics.nf @@ -5,7 +5,7 @@ include { NCBIDATASETS_SUMMARYGENOME as SUMMARYGENOME } from '../../modules/local/ncbidatasets/summarygenome' include { NCBIDATASETS_SUMMARYGENOME as SUMMARYSEQUENCE } from '../../modules/local/ncbidatasets/summarygenome' include { NCBI_GET_ODB } from '../../modules/local/ncbidatasets/get_odb' -include { BUSCO } from '../../modules/nf-core/busco/main' +include { BUSCO_BUSCO as BUSCO } from '../../modules/nf-core/busco/busco/main' include { RESTRUCTUREBUSCODIR } from '../../modules/local/restructurebuscodir' include { FASTK_FASTK } from '../../modules/nf-core/fastk/fastk/main' include { MERQURYFK_MERQURYFK } from '../../modules/nf-core/merquryfk/merquryfk/main' @@ -46,7 +46,7 @@ workflow GENOME_STATISTICS { | splitCsv() | map { row -> row[1] } | set { ch_lineage } - + BUSCO ( genome, "genome", ch_lineage, lineage_db.ifEmpty([]), [] ) ch_versions = ch_versions.mix ( BUSCO.out.versions.first() ) @@ -87,7 +87,7 @@ workflow GENOME_STATISTICS { FASTK_FASTK.out.hist | join ( FASTK_FASTK.out.ktab ) | set { ch_combo } - + ch_pacbio.dir | map { meta, dir -> [ meta, @@ -95,7 +95,7 @@ workflow GENOME_STATISTICS { dir.listFiles().findAll { it.toString().contains(".ktab") } .collect(), ] } | set { ch_grab } - + ch_combo | mix ( ch_grab ) | combine ( genome ) @@ -112,11 +112,11 @@ workflow GENOME_STATISTICS { SUMMARYGENOME.out.summary | join ( SUMMARYSEQUENCE.out.summary ) | set { ch_summary } - + BUSCO.out.short_summaries_json | ifEmpty ( [ [], [] ] ) | set { ch_busco } - + MERQURYFK_MERQURYFK.out.qv | join ( MERQURYFK_MERQURYFK.out.stats ) | map { meta, qv, comp -> [ meta + [ id: "merq" ], qv, comp ] }