diff --git a/modules/elprep/filter/main.nf b/modules/elprep/filter/main.nf new file mode 100644 index 00000000..5ca288bc --- /dev/null +++ b/modules/elprep/filter/main.nf @@ -0,0 +1,89 @@ +process ELPREP_FILTER { + tag "$meta.id" + label 'process_high' + + conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0': + 'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }" + + input: + tuple val(meta), path(bam) + val(run_haplotypecaller) + val(run_bqsr) + path(reference_sequences) + path(filter_regions_bed) + path(reference_elfasta) + path(known_sites_elsites) + path(target_regions_bed) + path(intermediate_bqsr_tables) + val(bqsr_tables_only) + val(get_activity_profile) + val(get_assembly_regions) + + + output: + tuple val(meta), path("output/**.{bam,sam}") ,emit: bam + tuple val(meta), path("*.metrics.txt") ,optional: true, emit: metrics + tuple val(meta), path("*.recall") ,optional: true, emit: recall + tuple val(meta), path("*.vcf.gz") ,optional: true, emit: gvcf + tuple val(meta), path("*.table") ,optional: true, emit: table + tuple val(meta), path("*.activity_profile.igv") ,optional: true, emit: activity_profile + tuple val(meta), path("*.assembly_regions.igv") ,optional: true, emit: assembly_regions + 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 suffix = args.contains("--output-type sam") ? "sam" : "bam" + + // filter args + def reference_sequences_cmd = reference_sequences ? " --replace-reference-sequences ${reference_sequences}" : "" + def filter_regions_cmd = filter_regions_bed ? " --filter-non-overlapping-reads ${filter_regions_bed}" : "" + + // markdup args + def markdup_cmd = args.contains("--mark-duplicates") ? " --mark-optical-duplicates ${prefix}.metrics.txt": "" + + // variant calling args + def haplotyper_cmd = run_haplotypecaller ? " --haplotypecaller ${prefix}.g.vcf.gz": "" + + def fasta_cmd = reference_elfasta ? " --reference ${reference_elfasta}": "" + def known_sites_cmd = known_sites_elsites ? " --known-sites ${known_sites_elsites}": "" + def target_regions_cmd = target_regions_bed ? " --target-regions ${target_regions_bed}": "" + + // bqsr args + def bqsr_cmd = run_bqsr ? " --bqsr ${prefix}.recall": "" + def bqsr_tables_only_cmd = bqsr_tables_only ? " --bqsr-tables-only ${prefix}.table": "" + + def intermediate_bqsr_cmd = intermediate_bqsr_tables ? " --bqsr-apply .": "" + + // misc + def activity_profile_cmd = get_activity_profile ? " --activity-profile ${prefix}.activity_profile.igv": "" + def assembly_regions_cmd = get_assembly_regions ? " --assembly-regions ${prefix}.assembly_regions.igv": "" + + """ + elprep filter ${bam} output/${prefix}.${suffix} \\ + ${reference_sequences_cmd} \\ + ${filter_regions_cmd} \\ + ${markdup_cmd} \\ + ${haplotyper_cmd} \\ + ${fasta_cmd} \\ + ${known_sites_cmd} \\ + ${target_regions_cmd} \\ + ${bqsr_cmd} \\ + ${bqsr_tables_only_cmd} \\ + ${intermediate_bqsr_cmd} \\ + ${activity_profile_cmd} \\ + ${assembly_regions_cmd} \\ + --nr-of-threads ${task.cpus} \\ + $args + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//') + END_VERSIONS + """ +} diff --git a/modules/elprep/filter/meta.yml b/modules/elprep/filter/meta.yml new file mode 100644 index 00000000..d7d41071 --- /dev/null +++ b/modules/elprep/filter/meta.yml @@ -0,0 +1,106 @@ +name: "elprep_filter" +description: "Filter, sort and markdup sam/bam files, with optional BQSR and variant calling." +keywords: + - sort + - bam + - sam + - filter + - variant calling +tools: + - "elprep": + description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4." + homepage: "https://github.com/ExaScience/elprep" + documentation: "https://github.com/ExaScience/elprep" + tool_dev_url: "https://github.com/ExaScience/elprep" + doi: "10.1371/journal.pone.0244471" + licence: "['AGPL v3']" + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: Input SAM/BAM file + pattern: "*.{bam,sam}" + - run_haplotypecaller: + type: boolean + description: Run variant calling on the input files. Needed to generate gvcf output. + - run_bqsr: + type: boolean + description: Run BQSR on the input files. Needed to generate recall metrics. + - reference_sequences: + type: file + description: Optional SAM header to replace existing header. + pattern: "*.sam" + - filter_regions_bed: + type: file + description: Optional BED file containing regions to filter. + pattern: "*.bed" + - reference_elfasta: + type: file + description: Elfasta file, required for BQSR and variant calling. + pattern: "*.elfasta" + - known_sites: + type: file + description: Optional elsites file containing known SNPs for BQSR. + pattern: "*.elsites" + - target_regions_bed: + type: file + description: Optional BED file containing target regions for BQSR and variant calling. + pattern: "*.bed" + - intermediate_bqsr_tables: + type: file + description: Optional list of BQSR tables, used when parsing files created by `elprep split` + pattern: "*.table" + - bqsr_tables_only: + type: boolean + description: Write intermediate BQSR tables, used when parsing files created by `elprep split`. + - get_activity_profile: + type: boolean + description: Get the activity profile calculated by the haplotypecaller to the given file in IGV format. + - get_assembly_regions: + type: boolean + description: Get the assembly regions calculated by haplotypecaller to the speficied file in IGV format. +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - bam: + type: file + description: Sorted, markdup, optionally BQSR BAM/SAM file + pattern: "*.{bam,sam}" + - metrics: + type: file + description: Optional duplicate metrics file generated by elprep + pattern: "*.{metrics.txt}" + - recall: + type: file + description: Optional recall metrics file generated by elprep + pattern: "*.{recall}" + - gvcf: + type: file + description: Optional GVCF output file + pattern: "*.{vcf.gz}" + - table: + type: file + description: Optional intermediate BQSR table output file + pattern: "*.{table}" + - activity_profile: + type: file + description: Optional activity profile output file + pattern: "*.{activity_profile.igv}" + - assembly_regions: + type: file + description: Optional activity regions output file + pattern: "*.{assembly_regions.igv}" +authors: + - "@matthdsm" diff --git a/modules/elprep/split/main.nf b/modules/elprep/split/main.nf new file mode 100644 index 00000000..639944ef --- /dev/null +++ b/modules/elprep/split/main.nf @@ -0,0 +1,45 @@ +process ELPREP_SPLIT { + tag "$meta.id" + label 'process_low' + + conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0': + 'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }" + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("output/**.{bam,sam}"), emit: bam + 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 single_end = meta.single_end ? " --single-end": "" + + """ + # create directory and move all input so elprep can find and merge them before splitting + mkdir input + mv ${bam} input/ + + mkdir ${prefix} + + elprep split \\ + input \\ + output/ \\ + $args \\ + $single_end \\ + --nr-of-threads $task.cpus \\ + --output-prefix $prefix + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//') + END_VERSIONS + """ +} diff --git a/modules/elprep/split/meta.yml b/modules/elprep/split/meta.yml new file mode 100644 index 00000000..b99562fa --- /dev/null +++ b/modules/elprep/split/meta.yml @@ -0,0 +1,43 @@ +name: "elprep_split" +description: Split bam file into manageable chunks +keywords: + - bam + - split by chromosome +tools: + - "elprep": + description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4." + homepage: "https://github.com/ExaScience/elprep" + documentation: "https://github.com/ExaScience/elprep" + tool_dev_url: "https://github.com/ExaScience/elprep" + doi: "10.1371" + licence: "['AGPL v3']" + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: List of BAM/SAM files + pattern: "*.{bam,sam}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + # + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - bam: + type: file + description: List of split BAM/SAM files + pattern: "*.{bam,sam}" + +authors: + - "@matthdsm" diff --git a/modules/kaiju/kaiju2table/main.nf b/modules/kaiju/kaiju2table/main.nf new file mode 100644 index 00000000..00739d1e --- /dev/null +++ b/modules/kaiju/kaiju2table/main.nf @@ -0,0 +1,40 @@ +process KAIJU_KAIJU2TABLE { + tag "$meta.id" + label 'process_low' + + conda (params.enable_conda ? "bioconda::kaiju=1.8.2" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/kaiju:1.8.2--h5b5514e_1': + 'quay.io/biocontainers/kaiju:1.8.2--h2e03b76_0' }" + + input: + tuple val(meta), path(results) + path db + val taxon_rank + + output: + tuple val(meta), path('*.txt'), emit: summary + 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}" + """ + dbnodes=`find -L ${db} -name "*nodes.dmp"` + dbname=`find -L ${db} -name "*.fmi" -not -name "._*"` + kaiju2table $args \\ + -t \$dbnodes \\ + -n \$dbname \\ + -r ${taxon_rank} \\ + -o ${prefix}.txt \\ + ${results} + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' )) + END_VERSIONS + """ +} diff --git a/modules/kaiju/kaiju2table/meta.yml b/modules/kaiju/kaiju2table/meta.yml new file mode 100644 index 00000000..bc3e85d7 --- /dev/null +++ b/modules/kaiju/kaiju2table/meta.yml @@ -0,0 +1,50 @@ +name: "kaiju_kaiju2table" +description: write your description here +keywords: + - classify + - metagenomics +tools: + - kaiju: + description: Fast and sensitive taxonomic classification for metagenomics + homepage: https://kaiju.binf.ku.dk/ + documentation: https://github.com/bioinformatics-centre/kaiju/blob/master/README.md + tool_dev_url: https://github.com/bioinformatics-centre/kaiju + doi: "10.1038/ncomms11257" + licence: ["GNU GPL v3"] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - results: + type: file + description: File containing the kaiju classification results + pattern: "*.{txt}" + - taxon_rank: + type: string + description: | + Taxonomic rank to display in report + pattern: "phylum|class|order|family|genus|species" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - results: + type: file + description: | + Summary table for a given taxonomic rank + pattern: "*.{tsv}" + +authors: + - "@sofstam" + - "@talnor" + - "@jfy133" diff --git a/modules/picard/collecthsmetrics/main.nf b/modules/picard/collecthsmetrics/main.nf index 3acf8bb8..ef7a9b9f 100644 --- a/modules/picard/collecthsmetrics/main.nf +++ b/modules/picard/collecthsmetrics/main.nf @@ -15,8 +15,8 @@ process PICARD_COLLECTHSMETRICS { path target_intervals output: - tuple val(meta), path("*collecthsmetrics.txt"), emit: hs_metrics - path "versions.yml" , emit: versions + tuple val(meta), path("*_metrics") , emit: metrics + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -41,7 +41,8 @@ process PICARD_COLLECTHSMETRICS { -BAIT_INTERVALS $bait_intervals \\ -TARGET_INTERVALS $target_intervals \\ -INPUT $bam \\ - -OUTPUT ${prefix}_collecthsmetrics.txt + -OUTPUT ${prefix}.CollectHsMetrics.coverage_metrics + cat <<-END_VERSIONS > versions.yml "${task.process}": @@ -52,7 +53,7 @@ process PICARD_COLLECTHSMETRICS { stub: def prefix = task.ext.prefix ?: "${meta.id}" """ - touch ${prefix}_collecthsmetrics.txt + touch ${prefix}.CollectHsMetrics.coverage_metrics cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/collecthsmetrics/meta.yml b/modules/picard/collecthsmetrics/meta.yml index 4b94909f..dc9d647a 100644 --- a/modules/picard/collecthsmetrics/meta.yml +++ b/modules/picard/collecthsmetrics/meta.yml @@ -57,10 +57,11 @@ output: type: file description: File containing software versions pattern: "versions.yml" - - hs_metrics: + - metrics: type: file - description: The metrics file. - pattern: "*_collecthsmetrics.txt" + description: Alignment metrics files generated by picard + pattern: "*_{metrics}" authors: - "@projectoriented" + - "@matthdsm" diff --git a/modules/samtools/view/main.nf b/modules/samtools/view/main.nf index 5f14fbbf..11cfb74b 100644 --- a/modules/samtools/view/main.nf +++ b/modules/samtools/view/main.nf @@ -8,7 +8,7 @@ process SAMTOOLS_VIEW { 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" input: - tuple val(meta), path(input) + tuple val(meta), path(input), path(index) path fasta output: diff --git a/modules/samtools/view/meta.yml b/modules/samtools/view/meta.yml index 5604bfa7..a8b43ecc 100644 --- a/modules/samtools/view/meta.yml +++ b/modules/samtools/view/meta.yml @@ -25,6 +25,10 @@ input: type: file description: BAM/CRAM/SAM file pattern: "*.{bam,cram,sam}" + - index: + type: optional file + description: BAM.BAI/CRAM.CRAI file + pattern: "*.{.bai,.crai}" - fasta: type: optional file description: Reference file the CRAM was created with diff --git a/modules/stranger/main.nf b/modules/stranger/main.nf index 55678bd3..ddfa0070 100644 --- a/modules/stranger/main.nf +++ b/modules/stranger/main.nf @@ -33,4 +33,15 @@ process STRANGER { stranger: \$( stranger --version ) END_VERSIONS """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + touch ${prefix}.vcf.gz + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + stranger: \$( stranger --version ) + END_VERSIONS + """ } diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index 4d7ba4fd..c33b626e 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -599,6 +599,14 @@ ectyper: - modules/ectyper/** - tests/modules/ectyper/** +elprep/filter: + - modules/elprep/filter/** + - tests/modules/elprep/filter/** + +elprep/split: + - modules/elprep/split/** + - tests/modules/elprep/split/** + emmtyper: - modules/emmtyper/** - tests/modules/emmtyper/** @@ -1001,6 +1009,10 @@ kaiju/kaiju: - modules/kaiju/kaiju/** - tests/modules/kaiju/kaiju/** +kaiju/kaiju2table: + - modules/kaiju/kaiju2table/** + - tests/modules/kaiju/kaiju2table/** + kallisto/index: - modules/kallisto/index/** - tests/modules/kallisto/index/** diff --git a/tests/config/test_data.config b/tests/config/test_data.config index ea123732..559c0d6f 100644 --- a/tests/config/test_data.config +++ b/tests/config/test_data.config @@ -112,6 +112,7 @@ params { } 'homo_sapiens' { 'genome' { + genome_elfasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome.elfasta" genome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta" genome_fasta_fai = "${test_data_dir}/genomics/homo_sapiens/genome/genome.fasta.fai" genome_dict = "${test_data_dir}/genomics/homo_sapiens/genome/genome.dict" @@ -123,6 +124,7 @@ params { genome_header = "${test_data_dir}/genomics/homo_sapiens/genome/genome.header" genome_bed_gz = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed.gz" genome_bed_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed.gz.tbi" + genome_elsites = "${test_data_dir}/genomics/homo_sapiens/genome/genome.elsites" transcriptome_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/transcriptome.fasta" genome2_fasta = "${test_data_dir}/genomics/homo_sapiens/genome/genome2.fasta" genome_chain_gz = "${test_data_dir}/genomics/homo_sapiens/genome/genome.chain.gz" @@ -136,6 +138,7 @@ params { genome_21_multi_interval_bed_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/multi_intervals.bed.gz.tbi" genome_21_chromosomes_dir = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/sequence/chromosomes.tar.gz" + dbsnp_146_hg38_elsites = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.elsites" dbsnp_146_hg38_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz" dbsnp_146_hg38_vcf_gz_tbi = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/dbsnp_146.hg38.vcf.gz.tbi" gnomad_r2_1_1_vcf_gz = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1.vcf.gz" diff --git a/tests/modules/elprep/filter/main.nf b/tests/modules/elprep/filter/main.nf new file mode 100644 index 00000000..0a8d43ca --- /dev/null +++ b/tests/modules/elprep/filter/main.nf @@ -0,0 +1,18 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { ELPREP_FILTER } from '../../../../modules/elprep/filter/main.nf' + +workflow test_elprep_filter { + + input = [ + [ id:'test', single_end:false ], // meta map + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) + ] + reference_elfasta = file(params.test_data['homo_sapiens']['genome']['genome_elfasta'], checkIfExists: true) + known_sites_elsites = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_elsites'], checkIfExists: true) + target_regions_bed = file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true) + + ELPREP_FILTER ( input, true, true, [], [], reference_elfasta, known_sites_elsites, target_regions_bed, [], [], true, true) +} diff --git a/tests/modules/elprep/filter/nextflow.config b/tests/modules/elprep/filter/nextflow.config new file mode 100644 index 00000000..d53a3d2d --- /dev/null +++ b/tests/modules/elprep/filter/nextflow.config @@ -0,0 +1,7 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + withName: ELPREP_FILTER { + ext.args = "--mark-duplicates " + } +} diff --git a/tests/modules/elprep/filter/test.yml b/tests/modules/elprep/filter/test.yml new file mode 100644 index 00000000..922d7a9b --- /dev/null +++ b/tests/modules/elprep/filter/test.yml @@ -0,0 +1,13 @@ +- name: elprep filter test_elprep_filter + command: nextflow run tests/modules/elprep/filter -entry test_elprep_filter -c tests/config/nextflow.config + tags: + - elprep + - elprep/filter + files: + - path: output/elprep/test.activity_profile.igv + - path: output/elprep/test.assembly_regions.igv + - path: output/elprep/output/test.bam + - path: output/elprep/test.g.vcf.gz + - path: output/elprep/test.metrics.txt + - path: output/elprep/test.recall + - path: output/elprep/versions.yml diff --git a/tests/modules/elprep/split/main.nf b/tests/modules/elprep/split/main.nf new file mode 100644 index 00000000..d5a111de --- /dev/null +++ b/tests/modules/elprep/split/main.nf @@ -0,0 +1,15 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { ELPREP_SPLIT } from '../../../../modules/elprep/split/main.nf' + +workflow test_elprep_split { + + input = [ + [ id:'test', single_end:false ], // meta map + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) + ] + + ELPREP_SPLIT ( input ) +} diff --git a/tests/modules/elprep/split/nextflow.config b/tests/modules/elprep/split/nextflow.config new file mode 100644 index 00000000..a3ae0169 --- /dev/null +++ b/tests/modules/elprep/split/nextflow.config @@ -0,0 +1,9 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + + withName : ELPREP_SPLIT { + ext.args = "--contig-group-size 1 --output-type bam" + } + +} diff --git a/tests/modules/elprep/split/test.yml b/tests/modules/elprep/split/test.yml new file mode 100644 index 00000000..2de3f99b --- /dev/null +++ b/tests/modules/elprep/split/test.yml @@ -0,0 +1,10 @@ +- name: elprep split test_elprep_split + command: nextflow run tests/modules/elprep/split -entry test_elprep_split -c tests/config/nextflow.config + tags: + - elprep + - elprep/split + files: + - path: output/elprep/output/splits/test-group00001.bam + - path: output/elprep/output/splits/test-unmapped.bam + - path: output/elprep/output/test-spread.bam + - path: output/elprep/versions.yml diff --git a/tests/modules/kaiju/kaiju2table/main.nf b/tests/modules/kaiju/kaiju2table/main.nf new file mode 100644 index 00000000..b7169ba5 --- /dev/null +++ b/tests/modules/kaiju/kaiju2table/main.nf @@ -0,0 +1,21 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { UNTAR } from '../../../../modules/untar/main.nf' +include { KAIJU_KAIJU } from '../../../../modules/kaiju/kaiju/main.nf' +include { KAIJU_KAIJU2TABLE } from '../../../../modules/kaiju/kaiju2table/main.nf' + +workflow test_kaiju_kaiju_single_end { + + input = [ + [ id:'test', single_end:true ], // meta map + file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) + ] + db = [ [], file(params.test_data['sarscov2']['genome']['kaiju_tar_gz'], checkIfExists: true) ] + taxon_rank = "species" + + ch_db = UNTAR ( db ) + KAIJU_KAIJU ( input, ch_db.untar.map{ it[1] } ) + KAIJU_KAIJU2TABLE ( KAIJU_KAIJU.out.results, ch_db.untar.map{ it[1] }, taxon_rank ) +} diff --git a/tests/modules/kaiju/kaiju2table/nextflow.config b/tests/modules/kaiju/kaiju2table/nextflow.config new file mode 100644 index 00000000..50f50a7a --- /dev/null +++ b/tests/modules/kaiju/kaiju2table/nextflow.config @@ -0,0 +1,5 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + +} \ No newline at end of file diff --git a/tests/modules/kaiju/kaiju2table/test.yml b/tests/modules/kaiju/kaiju2table/test.yml new file mode 100644 index 00000000..47d99c89 --- /dev/null +++ b/tests/modules/kaiju/kaiju2table/test.yml @@ -0,0 +1,9 @@ +- name: kaiju kaiju2table test_kaiju_kaiju_single_end + command: nextflow run tests/modules/kaiju/kaiju2table -entry test_kaiju_kaiju_single_end -c tests/config/nextflow.config + tags: + - kaiju + - kaiju/kaiju2table + files: + - path: output/kaiju/test.txt + md5sum: 0d9f8fd36fcf2888296ae12632c5f0a8 + - path: output/kaiju/versions.yml diff --git a/tests/modules/picard/collecthsmetrics/main.nf b/tests/modules/picard/collecthsmetrics/main.nf index 2e8727b5..a28eb174 100644 --- a/tests/modules/picard/collecthsmetrics/main.nf +++ b/tests/modules/picard/collecthsmetrics/main.nf @@ -7,7 +7,7 @@ include { PICARD_COLLECTHSMETRICS } from '../../../../modules/picard/collecthsme workflow test_picard_collecthsmetrics { input = [ [ id:'test', single_end:false ], // meta map - file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ] + file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ] fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) diff --git a/tests/modules/picard/collecthsmetrics/test.yml b/tests/modules/picard/collecthsmetrics/test.yml index 9232d508..9aa14f15 100644 --- a/tests/modules/picard/collecthsmetrics/test.yml +++ b/tests/modules/picard/collecthsmetrics/test.yml @@ -5,4 +5,4 @@ - picard/collecthsmetrics files: # The file can't be md5'd consistently - - path: output/picard/test_collecthsmetrics.txt + - path: output/picard/test.CollectHsMetrics.coverage_metrics diff --git a/tests/modules/samtools/view/main.nf b/tests/modules/samtools/view/main.nf index 8ee27ef8..9c239066 100644 --- a/tests/modules/samtools/view/main.nf +++ b/tests/modules/samtools/view/main.nf @@ -6,7 +6,8 @@ include { SAMTOOLS_VIEW } from '../../../../modules/samtools/view/main.nf' workflow test_samtools_view { input = [ [ id:'test', single_end:false ], // meta map - file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) + file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true), + [] ] SAMTOOLS_VIEW ( input, [] ) @@ -14,8 +15,8 @@ workflow test_samtools_view { workflow test_samtools_view_cram { input = [ [ id: 'test' ], // meta map - file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true), - file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true) + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram'], checkIfExists: true), + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_recalibrated_sorted_cram_crai'], checkIfExists: true) ] fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true) diff --git a/tests/modules/stranger/main.nf b/tests/modules/stranger/main.nf index 5bd6766b..4a930c19 100644 --- a/tests/modules/stranger/main.nf +++ b/tests/modules/stranger/main.nf @@ -23,3 +23,8 @@ workflow test_stranger_without_optional_variant_catalog { EXPANSIONHUNTER ( input, fasta, variant_catalog ) STRANGER ( EXPANSIONHUNTER.out.vcf, [] ) } + +workflow test_stranger_without_optional_variant_catalog_stubs { + EXPANSIONHUNTER ( input, fasta, variant_catalog ) + STRANGER ( EXPANSIONHUNTER.out.vcf, [] ) +} diff --git a/tests/modules/stranger/test.yml b/tests/modules/stranger/test.yml index c7a6972e..bf922c86 100644 --- a/tests/modules/stranger/test.yml +++ b/tests/modules/stranger/test.yml @@ -25,3 +25,13 @@ md5sum: bbe15159195681d5c18596d3ad85c78f - path: output/stranger/versions.yml md5sum: 8558542a007e90ea5dcdceed3f12585d + +- name: stranger test_stranger_without_optional_variant_catalog_stubs + command: nextflow run tests/modules/stranger -entry test_stranger_without_optional_variant_catalog -c tests/config/nextflow.config -stub-run + tags: + - stranger + files: + - path: output/expansionhunter/test.vcf + - path: output/expansionhunter/versions.yml + - path: output/stranger/test.vcf.gz + - path: output/stranger/versions.yml