diff --git a/conf/modules.config b/conf/modules.config index d8fb382..b707954 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -164,6 +164,47 @@ process { ] } + withName: MINIMAP2_INDEX { + ext.args = '-x map-ont' + publishDir = [ + path: { "${params.outdir}/minimap2/index" }, + mode: params.publish_dir_mode, + enabled: params.save_minimap2_hostremoval_index, + pattern: 'minimap2' + ] + } + + withName: MINIMAP2_ALIGN { + ext.prefix = { "${meta.id}_${meta.run_accession}" } + publishDir = [ + path: { "${params.outdir}/minimap2/align" }, + mode: params.publish_dir_mode, + enabled: params.save_minimap2_hostremoval_mapped, + pattern: '*.bam' + ] + } + + withName: SAMTOOLS_VIEW { + ext.args = '-f 4' + ext.prefix = { "${meta.id}.mapped.sorted" } + publishDir = [ + path: { "${params.outdir}/samtools/view" }, + mode: params.publish_dir_mode, + enabled: params.save_samtools_unmapped_bam, + pattern: '*.bam' + ] + } + + withName: SAMTOOLS_BAM2FQ { + ext.prefix = { "${meta.id}_${meta.run_accession}" } + publishDir = [ + path: { "${params.outdir}/samtools/bam2fq" }, + mode: params.publish_dir_mode, + enabled: params.save_minimap2_unmapped_fq, + pattern: '*.fq.gz' + ] + } + withName: BBMAP_BBDUK { ext.args = [ "entropy=${params.shortread_complexityfilter_entropy}", diff --git a/modules.json b/modules.json index a65926c..071234d 100644 --- a/modules.json +++ b/modules.json @@ -52,6 +52,12 @@ "git_sha": "2d38566eca4cc15142b2ffa7c11837569b39aece" }, "metaphlan3": { + "git_sha": "ed4dd1a928ebf4308efb720de878045f7773f8e2" + }, + "minimap2/align": { + "git_sha": "1a5a9e7b4009dcf34e6867dd1a5a1d9a718b027b" + }, + "minimap2/index": { "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d" }, "multiqc": { @@ -63,9 +69,15 @@ "prinseqplusplus": { "git_sha": "f1c5384c31e985591716afdd732cf8c2ae29d05b" }, + "samtools/bam2fq": { + "git_sha": "897c33d5da084b61109500ee44c01da2d3e4e773" + }, + "samtools/view": { + "git_sha": "12afb6b0faf3cabf769c9a2a7dd477e3f066eac0" + }, "untar": { "git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918" } } } -} +} \ No newline at end of file diff --git a/modules/nf-core/modules/metaphlan3/main.nf b/modules/nf-core/modules/metaphlan3/main.nf index 3fc6b27..bff0eb9 100644 --- a/modules/nf-core/modules/metaphlan3/main.nf +++ b/modules/nf-core/modules/metaphlan3/main.nf @@ -23,7 +23,7 @@ process METAPHLAN3 { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" - def input_type = ("$input".endsWith(".fastq.gz")) ? "--input_type fastq" : ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam" + def input_type = ("$input".endsWith(".fastq.gz") || "$input".endsWith(".fq.gz")) ? "--input_type fastq" : ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam" def input_data = ("$input_type".contains("fastq")) && !meta.single_end ? "${input[0]},${input[1]}" : "$input" def bowtie2_out = "$input_type" == "--input_type bowtie2out" || "$input_type" == "--input_type sam" ? '' : "--bowtie2out ${prefix}.bowtie2out.txt" diff --git a/modules/nf-core/modules/minimap2/align/main.nf b/modules/nf-core/modules/minimap2/align/main.nf new file mode 100644 index 0000000..08ac6ee --- /dev/null +++ b/modules/nf-core/modules/minimap2/align/main.nf @@ -0,0 +1,48 @@ +process MINIMAP2_ALIGN { + tag "$meta.id" + label 'process_medium' + + conda (params.enable_conda ? 'bioconda::minimap2=2.21 bioconda::samtools=1.12' : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' : + 'quay.io/biocontainers/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' }" + + input: + tuple val(meta), path(reads) + path reference + val bam_format + val cigar_paf_format + val cigar_bam + + output: + tuple val(meta), path("*.paf"), optional: true, emit: paf + tuple val(meta), path("*.bam"), optional: true, emit: bam + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def input_reads = meta.single_end ? "$reads" : "${reads[0]} ${reads[1]}" + def bam_output = bam_format ? "-a | samtools sort | samtools view -@ ${task.cpus} -b -h -o ${prefix}.bam" : "-o ${prefix}.paf" + def cigar_paf = cigar_paf_format && !bam_format ? "-c" : '' + def set_cigar_bam = cigar_bam && bam_format ? "-L" : '' + """ + minimap2 \\ + $args \\ + -t $task.cpus \\ + $reference \\ + $input_reads \\ + $cigar_paf \\ + $set_cigar_bam \\ + $bam_output + + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + minimap2: \$(minimap2 --version 2>&1) + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/minimap2/align/meta.yml b/modules/nf-core/modules/minimap2/align/meta.yml new file mode 100644 index 0000000..991b39a --- /dev/null +++ b/modules/nf-core/modules/minimap2/align/meta.yml @@ -0,0 +1,65 @@ +name: minimap2_align +description: A versatile pairwise aligner for genomic and spliced nucleotide sequences +keywords: + - align + - fasta + - fastq + - genome + - paf + - reference +tools: + - minimap2: + description: | + A versatile pairwise aligner for genomic and spliced nucleotide sequences. + homepage: https://github.com/lh3/minimap2 + documentation: https://github.com/lh3/minimap2#uguide + licence: ["MIT"] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: | + List of input FASTA or FASTQ files of size 1 and 2 for single-end + and paired-end data, respectively. + - reference: + type: file + description: | + Reference database in FASTA format. + - bam_format: + type: boolean + description: Specify that output should be in BAM format + - cigar_paf_format: + type: boolean + description: Specify that output CIGAR should be in PAF format + - cigar_bam: + type: boolean + description: | + Write CIGAR with >65535 ops at the CG tag. This is recommended when + doing XYZ (https://github.com/lh3/minimap2#working-with-65535-cigar-operations) +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - paf: + type: file + description: Alignment in PAF format + pattern: "*.paf" + - bam: + type: file + description: Alignment in BAM format + pattern: "*.bam" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@heuermh" + - "@sofstam" + - "@sateeshperi" + - "@jfy133" diff --git a/modules/nf-core/modules/minimap2/index/main.nf b/modules/nf-core/modules/minimap2/index/main.nf new file mode 100644 index 0000000..3dfeb86 --- /dev/null +++ b/modules/nf-core/modules/minimap2/index/main.nf @@ -0,0 +1,33 @@ +process MINIMAP2_INDEX { + label 'process_medium' + + conda (params.enable_conda ? 'bioconda::minimap2=2.21' : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/minimap2:2.21--h5bf99c6_0' : + 'quay.io/biocontainers/minimap2:2.21--h5bf99c6_0' }" + + input: + path fasta + + output: + path "*.mmi" , emit: index + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + """ + minimap2 \\ + -t $task.cpus \\ + -d ${fasta.baseName}.mmi \\ + $args \\ + $fasta + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + minimap2: \$(minimap2 --version 2>&1) + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/minimap2/index/meta.yml b/modules/nf-core/modules/minimap2/index/meta.yml new file mode 100644 index 0000000..3bf9f04 --- /dev/null +++ b/modules/nf-core/modules/minimap2/index/meta.yml @@ -0,0 +1,30 @@ +name: minimap2_index +description: Provides fasta index required by minimap2 alignment. +keywords: + - index + - fasta + - reference +tools: + - minimap2: + description: | + A versatile pairwise aligner for genomic and spliced nucleotide sequences. + homepage: https://github.com/lh3/minimap2 + documentation: https://github.com/lh3/minimap2#uguide + licence: ["MIT"] +input: + - fasta: + type: file + description: | + Reference database in FASTA format. +output: + - mmi: + type: file + description: Minimap2 fasta index. + pattern: "*.mmi" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@yuukiiwa" + - "@drpatelh" diff --git a/modules/nf-core/modules/samtools/bam2fq/main.nf b/modules/nf-core/modules/samtools/bam2fq/main.nf new file mode 100644 index 0000000..554af48 --- /dev/null +++ b/modules/nf-core/modules/samtools/bam2fq/main.nf @@ -0,0 +1,56 @@ +process SAMTOOLS_BAM2FQ { + tag "$meta.id" + label 'process_low' + + conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : + 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + + input: + tuple val(meta), path(inputbam) + val split + + output: + tuple val(meta), path("*.fq.gz"), emit: reads + 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}" + + if (split){ + """ + samtools \\ + bam2fq \\ + $args \\ + -@ $task.cpus \\ + -1 ${prefix}_1.fq.gz \\ + -2 ${prefix}_2.fq.gz \\ + -0 ${prefix}_other.fq.gz \\ + -s ${prefix}_singleton.fq.gz \\ + $inputbam + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ + } else { + """ + samtools \\ + bam2fq \\ + $args \\ + -@ $task.cpus \\ + $inputbam | gzip > ${prefix}_interleaved.fq.gz + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ + } +} diff --git a/modules/nf-core/modules/samtools/bam2fq/meta.yml b/modules/nf-core/modules/samtools/bam2fq/meta.yml new file mode 100644 index 0000000..319a60c --- /dev/null +++ b/modules/nf-core/modules/samtools/bam2fq/meta.yml @@ -0,0 +1,55 @@ +name: samtools_bam2fq +description: | + The module uses bam2fq method from samtools to + convert a SAM, BAM or CRAM file to FASTQ format +keywords: + - bam2fq + - samtools + - fastq +tools: + - samtools: + description: Tools for dealing with SAM, BAM and CRAM files + homepage: None + documentation: http://www.htslib.org/doc/1.1/samtools.html + tool_dev_url: None + doi: "" + licence: ["MIT"] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - inputbam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - split: + type: boolean + description: | + TRUE/FALSE value to indicate if reads should be separated into + /1, /2 and if present other, or singleton. + Note: choosing TRUE will generate 4 different files. + Choosing FALSE will produce a single file, which will be interleaved in case + the input contains paired reads. + +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" + - reads: + type: file + description: | + FASTQ files, which will be either a group of 4 files (read_1, read_2, other and singleton) + or a single interleaved .fq.gz file if the user chooses not to split the reads. + pattern: "*.fq.gz" + +authors: + - "@lescai" diff --git a/modules/nf-core/modules/samtools/view/main.nf b/modules/nf-core/modules/samtools/view/main.nf new file mode 100644 index 0000000..11cfb74 --- /dev/null +++ b/modules/nf-core/modules/samtools/view/main.nf @@ -0,0 +1,44 @@ +process SAMTOOLS_VIEW { + tag "$meta.id" + label 'process_medium' + + conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : + 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + + input: + tuple val(meta), path(input), path(index) + path fasta + + output: + tuple val(meta), path("*.bam") , emit: bam , optional: true + tuple val(meta), path("*.cram"), emit: cram, optional: true + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def args2 = task.ext.args2 ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def reference = fasta ? "--reference ${fasta} -C" : "" + def file_type = input.getExtension() + if ("$input" == "${prefix}.${file_type}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!" + """ + samtools \\ + view \\ + --threads ${task.cpus-1} \\ + ${reference} \\ + $args \\ + $input \\ + $args2 \\ + > ${prefix}.${file_type} + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/modules/samtools/view/meta.yml b/modules/nf-core/modules/samtools/view/meta.yml new file mode 100644 index 0000000..a8b43ec --- /dev/null +++ b/modules/nf-core/modules/samtools/view/meta.yml @@ -0,0 +1,57 @@ +name: samtools_view +description: filter/convert SAM/BAM/CRAM file +keywords: + - view + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 + licence: ["MIT"] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - 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 + pattern: "*.{fasta,fa}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: filtered/converted BAM/SAM file + pattern: "*.{bam,sam}" + - cram: + type: file + description: filtered/converted CRAM file + pattern: "*.cram" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@drpatelh" + - "@joseespinosa" + - "@FriederikeHanssen" diff --git a/nf-core/modules/samtools/bam2fq/main.nf b/nf-core/modules/samtools/bam2fq/main.nf new file mode 100644 index 0000000..5d6aa79 --- /dev/null +++ b/nf-core/modules/samtools/bam2fq/main.nf @@ -0,0 +1,56 @@ +process SAMTOOLS_BAM2FQ { + tag "$meta.id" + label 'process_low' + + conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : + 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + + input: + tuple val(meta), path(inputbam) + val split + + output: + tuple val(meta), path("*.fq.gz"), emit: reads + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + + if (split){ + """ + samtools \\ + bam2fq \\ + $args \\ + -@ $task.cpus \\ + -1 ${prefix}_1.fq.gz \\ + -2 ${prefix}_2.fq.gz \\ + -0 ${prefix}_other.fq.gz \\ + -s ${prefix}_singleton.fq.gz \\ + $inputbam + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ + } else { + """ + samtools \\ + bam2fq \\ + $args \\ + -@ $task.cpus \\ + $inputbam >${prefix}_interleaved.fq.gz + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ + } +} diff --git a/nf-core/modules/samtools/bam2fq/meta.yml b/nf-core/modules/samtools/bam2fq/meta.yml new file mode 100644 index 0000000..319a60c --- /dev/null +++ b/nf-core/modules/samtools/bam2fq/meta.yml @@ -0,0 +1,55 @@ +name: samtools_bam2fq +description: | + The module uses bam2fq method from samtools to + convert a SAM, BAM or CRAM file to FASTQ format +keywords: + - bam2fq + - samtools + - fastq +tools: + - samtools: + description: Tools for dealing with SAM, BAM and CRAM files + homepage: None + documentation: http://www.htslib.org/doc/1.1/samtools.html + tool_dev_url: None + doi: "" + licence: ["MIT"] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - inputbam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - split: + type: boolean + description: | + TRUE/FALSE value to indicate if reads should be separated into + /1, /2 and if present other, or singleton. + Note: choosing TRUE will generate 4 different files. + Choosing FALSE will produce a single file, which will be interleaved in case + the input contains paired reads. + +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" + - reads: + type: file + description: | + FASTQ files, which will be either a group of 4 files (read_1, read_2, other and singleton) + or a single interleaved .fq.gz file if the user chooses not to split the reads. + pattern: "*.fq.gz" + +authors: + - "@lescai"