diff --git a/modules.json b/modules.json index 7311c12b..56ce0b4a 100644 --- a/modules.json +++ b/modules.json @@ -3,14 +3,14 @@ "homePage": "https://github.com/nf-core/blobtoolkit", "repos": { "nf-core/modules": { - "custom/dumpsoftwareversions": { - "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" + "busco": { + "git_sha": "9fa6b6c1fc930830c1d819a9273b4ec12ffacb0a" }, - "fastqc": { + "custom/dumpsoftwareversions": { "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" }, - "multiqc": { - "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" + "mosdepth": { + "git_sha": "72a31b76eb1b58879e0d91fb1d992e0118693098" } } } diff --git a/modules/nf-core/modules/busco/main.nf b/modules/nf-core/modules/busco/main.nf new file mode 100644 index 00000000..f0713862 --- /dev/null +++ b/modules/nf-core/modules/busco/main.nf @@ -0,0 +1,84 @@ +process BUSCO { + tag "$meta.id" + label 'process_medium' + + conda (params.enable_conda ? "bioconda::busco=5.3.2" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/busco:5.3.2--pyhdfd78af_0': + 'quay.io/biocontainers/busco:5.3.2--pyhdfd78af_0' }" + + input: + tuple val(meta), path('tmp_input/*') + each lineage // Required: lineage to check against, "auto" enables --auto-lineage instead + path busco_lineages_path // Recommended: path to busco lineages - downloads if not set + path config_file // Optional: busco configuration file + + 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") , emit: busco_dir + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}-${lineage}" + def busco_config = config_file ? "--config $config_file" : '' + def busco_lineage = lineage.equals('auto') ? '--auto-lineage' : "--lineage_dataset ${lineage}" + def busco_lineage_dir = busco_lineages_path ? "--offline --download_path ${busco_lineages_path}" : '' + """ + # Nextflow changes the container --entrypoint to /bin/bash (container default entrypoint: /usr/local/env-execute) + # Check for container variable initialisation script and source it. + if [ -f "/usr/local/env-activate.sh" ]; then + set +u # Otherwise, errors out because of various unbound variables + . "/usr/local/env-activate.sh" + set -u + fi + + # If the augustus config directory is not writable, then copy to writeable area + if [ ! -w "\${AUGUSTUS_CONFIG_PATH}" ]; then + # Create writable tmp directory for augustus + AUG_CONF_DIR=\$( mktemp -d -p \$PWD ) + cp -r \$AUGUSTUS_CONFIG_PATH/* \$AUG_CONF_DIR + export AUGUSTUS_CONFIG_PATH=\$AUG_CONF_DIR + echo "New AUGUSTUS_CONFIG_PATH=\${AUGUSTUS_CONFIG_PATH}" + fi + + # Ensure the input is uncompressed + INPUT_SEQS=input_seqs + mkdir "\$INPUT_SEQS" + cd "\$INPUT_SEQS" + for FASTA in ../tmp_input/*; do + if [ "\${FASTA##*.}" == 'gz' ]; then + gzip -cdf "\$FASTA" > \$( basename "\$FASTA" .gz ) + else + ln -s "\$FASTA" . + fi + done + cd .. + + busco \\ + --cpu $task.cpus \\ + --in "\$INPUT_SEQS" \\ + --out ${prefix}-busco \\ + $busco_lineage \\ + $busco_lineage_dir \\ + $busco_config \\ + $args + + # clean up + rm -rf "\$INPUT_SEQS" + + # Move files to avoid staging/publishing issues + mv ${prefix}-busco/batch_summary.txt ${prefix}-busco.batch_summary.txt + mv ${prefix}-busco/*/short_summary.*.{json,txt} . || echo "Short summaries were not available: No genes were found." + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' ) + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/busco/meta.yml b/modules/nf-core/modules/busco/meta.yml new file mode 100644 index 00000000..ef8c5245 --- /dev/null +++ b/modules/nf-core/modules/busco/meta.yml @@ -0,0 +1,69 @@ +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}" + - lineage: + type: value + 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" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + +authors: + - "@priyanka-surana" + - "@charles-plessy" + - "@mahesh-panchal" + - "@muffato" + - "@jvhagey" diff --git a/modules/nf-core/modules/fastqc/main.nf b/modules/nf-core/modules/fastqc/main.nf deleted file mode 100644 index ed6b8c50..00000000 --- a/modules/nf-core/modules/fastqc/main.nf +++ /dev/null @@ -1,47 +0,0 @@ -process FASTQC { - tag "$meta.id" - label 'process_medium' - - conda (params.enable_conda ? "bioconda::fastqc=0.11.9" : null) - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/fastqc:0.11.9--0' : - 'quay.io/biocontainers/fastqc:0.11.9--0' }" - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.html"), emit: html - tuple val(meta), path("*.zip") , emit: zip - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - // Add soft-links to original FastQs for consistent naming in pipeline - def prefix = task.ext.prefix ?: "${meta.id}" - if (meta.single_end) { - """ - [ ! -f ${prefix}.fastq.gz ] && ln -s $reads ${prefix}.fastq.gz - fastqc $args --threads $task.cpus ${prefix}.fastq.gz - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) - END_VERSIONS - """ - } else { - """ - [ ! -f ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz - [ ! -f ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz - fastqc $args --threads $task.cpus ${prefix}_1.fastq.gz ${prefix}_2.fastq.gz - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed -e "s/FastQC v//g" ) - END_VERSIONS - """ - } -} diff --git a/modules/nf-core/modules/fastqc/meta.yml b/modules/nf-core/modules/fastqc/meta.yml deleted file mode 100644 index 4da5bb5a..00000000 --- a/modules/nf-core/modules/fastqc/meta.yml +++ /dev/null @@ -1,52 +0,0 @@ -name: fastqc -description: Run FastQC on sequenced reads -keywords: - - quality control - - qc - - adapters - - fastq -tools: - - fastqc: - description: | - FastQC gives general quality metrics about your reads. - It provides information about the quality score distribution - across your reads, the per base sequence content (%A/C/G/T). - You get information about adapter contamination and other - overrepresented sequences. - homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ - documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ - licence: ["GPL-2.0-only"] -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - html: - type: file - description: FastQC report - pattern: "*_{fastqc.html}" - - zip: - type: file - description: FastQC report archive - pattern: "*_{fastqc.zip}" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@drpatelh" - - "@grst" - - "@ewels" - - "@FelixKrueger" diff --git a/modules/nf-core/modules/mosdepth/main.nf b/modules/nf-core/modules/mosdepth/main.nf new file mode 100644 index 00000000..d7e3c929 --- /dev/null +++ b/modules/nf-core/modules/mosdepth/main.nf @@ -0,0 +1,81 @@ +process MOSDEPTH { + tag "$meta.id" + label 'process_medium' + + conda (params.enable_conda ? 'bioconda::mosdepth=0.3.3' : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/mosdepth:0.3.3--hdfd78af_1' : + 'quay.io/biocontainers/mosdepth:0.3.3--hdfd78af_1'}" + + input: + tuple val(meta), path(bam), path(bai) + path bed + path fasta + + output: + tuple val(meta), path('*.global.dist.txt') , emit: global_txt + tuple val(meta), path('*.summary.txt') , emit: summary_txt + tuple val(meta), path('*.region.dist.txt') , optional:true, emit: regions_txt + tuple val(meta), path('*.per-base.d4') , optional:true, emit: per_base_d4 + tuple val(meta), path('*.per-base.bed.gz') , optional:true, emit: per_base_bed + tuple val(meta), path('*.per-base.bed.gz.csi') , optional:true, emit: per_base_csi + tuple val(meta), path('*.regions.bed.gz') , optional:true, emit: regions_bed + tuple val(meta), path('*.regions.bed.gz.csi') , optional:true, emit: regions_csi + tuple val(meta), path('*.quantized.bed.gz') , optional:true, emit: quantized_bed + tuple val(meta), path('*.quantized.bed.gz.csi') , optional:true, emit: quantized_csi + tuple val(meta), path('*.thresholds.bed.gz') , optional:true, emit: thresholds_bed + tuple val(meta), path('*.thresholds.bed.gz.csi'), optional:true, emit: thresholds_csi + 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 reference = fasta ? "--fasta ${fasta}" : "" + def interval = bed ? "--by ${bed}" : "" + if (bed && args.contains("--by")) { + exit 1, "'--by' can only be specified once when running mosdepth! Either remove input BED file definition or remove '--by' from 'ext.args' definition" + } + if (!bed && args.contains("--thresholds")) { + exit 1, "'--thresholds' can only be specified in conjunction with '--by'" + } + + """ + mosdepth \\ + --threads $task.cpus \\ + $interval \\ + $reference \\ + $args \\ + $prefix \\ + $bam + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + mosdepth: \$(mosdepth --version 2>&1 | sed 's/^.*mosdepth //; s/ .*\$//') + END_VERSIONS + """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + touch ${prefix}.global.dist.txt + touch ${prefix}.region.dist.txt + touch ${prefix}.summary.txt + touch ${prefix}.per-base.d4 + touch ${prefix}.per-base.bed.gz + touch ${prefix}.per-base.bed.gz.csi + touch ${prefix}.regions.bed.gz + touch ${prefix}.regions.bed.gz.csi + touch ${prefix}.quantized.bed.gz + touch ${prefix}.quantized.bed.gz.csi + touch ${prefix}.thresholds.bed.gz + touch ${prefix}.thresholds.bed.gz.csi + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + mosdepth: \$(mosdepth --version 2>&1 | sed 's/^.*mosdepth //; s/ .*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/mosdepth/meta.yml b/modules/nf-core/modules/mosdepth/meta.yml new file mode 100644 index 00000000..d1e33447 --- /dev/null +++ b/modules/nf-core/modules/mosdepth/meta.yml @@ -0,0 +1,99 @@ +name: mosdepth +description: Calculates genome-wide sequencing coverage. +keywords: + - mosdepth + - bam + - cram + - coverage +tools: + - mosdepth: + description: | + Fast BAM/CRAM depth calculation for WGS, exome, or targeted sequencing. + documentation: https://github.com/brentp/mosdepth + doi: 10.1093/bioinformatics/btx699 + licence: ["MIT"] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: Input BAM/CRAM file + pattern: "*.{bam,cram}" + - bai: + type: file + description: Index for BAM/CRAM file + pattern: "*.{bai,crai}" + - bed: + type: file + description: BED file with intersected intervals + pattern: "*.{bed}" + - fasta: + type: file + description: Reference genome FASTA file + pattern: "*.{fa,fasta}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - global_txt: + type: file + description: Text file with global cumulative coverage distribution + pattern: "*.{global.dist.txt}" + - regions_txt: + type: file + description: Text file with region cumulative coverage distribution + pattern: "*.{region.dist.txt}" + - summary_txt: + type: file + description: Text file with summary mean depths per chromosome and regions + pattern: "*.{summary.txt}" + - per_base_bed: + type: file + description: BED file with per-base coverage + pattern: "*.{per-base.bed.gz}" + - per_base_csi: + type: file + description: Index file for BED file with per-base coverage + pattern: "*.{per-base.bed.gz.csi}" + - per_base_d4: + type: file + description: D4 file with per-base coverage + pattern: "*.{per-base.d4}" + - regions_bed: + type: file + description: BED file with per-region coverage + pattern: "*.{regions.bed.gz}" + - regions_csi: + type: file + description: Index file for BED file with per-region coverage + pattern: "*.{regions.bed.gz.csi}" + - quantized_bed: + type: file + description: BED file with binned coverage + pattern: "*.{quantized.bed.gz}" + - quantized_csi: + type: file + description: Index file for BED file with binned coverage + pattern: "*.{quantized.bed.gz.csi}" + - thresholds_bed: + type: file + description: BED file with the number of bases in each region that are covered at or above each threshold + pattern: "*.{thresholds.bed.gz}" + - thresholds_csi: + type: file + description: Index file for BED file with threshold coverage + pattern: "*.{thresholds.bed.gz.csi}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@joseespinosa" + - "@drpatelh" + - "@ramprasadn" + - "@matthdsm" diff --git a/modules/nf-core/modules/multiqc/main.nf b/modules/nf-core/modules/multiqc/main.nf deleted file mode 100644 index 1264aac1..00000000 --- a/modules/nf-core/modules/multiqc/main.nf +++ /dev/null @@ -1,31 +0,0 @@ -process MULTIQC { - label 'process_medium' - - conda (params.enable_conda ? 'bioconda::multiqc=1.12' : null) - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.12--pyhdfd78af_0' : - 'quay.io/biocontainers/multiqc:1.12--pyhdfd78af_0' }" - - input: - path multiqc_files - - output: - path "*multiqc_report.html", emit: report - path "*_data" , emit: data - path "*_plots" , optional:true, emit: plots - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - """ - multiqc -f $args . - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - multiqc: \$( multiqc --version | sed -e "s/multiqc, version //g" ) - END_VERSIONS - """ -} diff --git a/modules/nf-core/modules/multiqc/meta.yml b/modules/nf-core/modules/multiqc/meta.yml deleted file mode 100644 index 6fa891ef..00000000 --- a/modules/nf-core/modules/multiqc/meta.yml +++ /dev/null @@ -1,40 +0,0 @@ -name: MultiQC -description: Aggregate results from bioinformatics analyses across many samples into a single report -keywords: - - QC - - bioinformatics tools - - Beautiful stand-alone HTML report -tools: - - multiqc: - description: | - MultiQC searches a given directory for analysis logs and compiles a HTML report. - It's a general use tool, perfect for summarising the output from numerous bioinformatics tools. - homepage: https://multiqc.info/ - documentation: https://multiqc.info/docs/ - licence: ["GPL-3.0-or-later"] -input: - - multiqc_files: - type: file - description: | - List of reports / files recognised by MultiQC, for example the html and zip output of FastQC -output: - - report: - type: file - description: MultiQC report file - pattern: "multiqc_report.html" - - data: - type: dir - description: MultiQC data dir - pattern: "multiqc_data" - - plots: - type: file - description: Plots created by MultiQC - pattern: "*_data" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@abhi18av" - - "@bunop" - - "@drpatelh"