diff --git a/modules/nf-core/nextdenovo/environment.yml b/modules/nf-core/nextdenovo/environment.yml new file mode 100644 index 00000000000..3192ce89809 --- /dev/null +++ b/modules/nf-core/nextdenovo/environment.yml @@ -0,0 +1,11 @@ +channels: + - conda-forge + - bioconda +dependencies: + - bioconda::nextdenovo=2.5.2 + - pip=23.3.1 + - pip: + - paralleltask==0.1.1 + - python=3.8 + + \ No newline at end of file diff --git a/modules/nf-core/nextdenovo/main.nf b/modules/nf-core/nextdenovo/main.nf new file mode 100644 index 00000000000..fad29d16393 --- /dev/null +++ b/modules/nf-core/nextdenovo/main.nf @@ -0,0 +1,54 @@ +process NEXTDENOVO { + tag "$meta.id" + label 'process_high' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/nextdenovo:2.5.2--py310h0ceaa1d_6' : + 'biocontainers/nextdenovo:2.5.2--py310h0ceaa1d_6' }" + + input: + tuple val(meta), path(reads) + path config + + output: + tuple val(meta), path("*.fasta.gz"), emit: fasta + tuple val(meta), path("*.stat") , emit: stat + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + echo "parallel_jobs = ${task.cpus}" >> conf.cfg + cat $config >> conf.cfg + echo ${reads} > input.fofn + nextDenovo \\ + conf.cfg \\ + input.fofn \\ + + gzip -c ./03.ctg_graph/nd.asm.fasta > ${prefix}.assembly.fasta.gz + + mv ./03.ctg_graph/nd.asm.fasta.stat ${prefix}.assembly_info.stat + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + \$( nextDenovo --version ) + END_VERSIONS + """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + echo stub | gzip -c > ${prefix}.assembly.fasta.gz + echo contig_1 > ${prefix}.assembly_info.stat + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + \$( nextDenovo --version ) + END_VERSIONS + """ +} diff --git a/modules/nf-core/nextdenovo/meta.yml b/modules/nf-core/nextdenovo/meta.yml new file mode 100644 index 00000000000..55bbb2a59bc --- /dev/null +++ b/modules/nf-core/nextdenovo/meta.yml @@ -0,0 +1,68 @@ +name: "nextdenovo" +description: NextDenovo is a string graph-based de novo assembler for long reads (CLR, + HiFi and ONT). It uses a “correct-then-assemble” strategy similar to canu (no correction + step for PacBio HiFi reads), but requires significantly less computing resources + and storages +keywords: + - assembly + - genome + - de novo + - genome assembler + - single molecule +tools: + - "nextdenovo": + description: "NextDenovo is a string graph-based de novo assembler for long reads + (CLR, HiFi and ONT). It uses a “correct-then-assemble” strategy similar to canu + (no correction step for PacBio HiFi reads), but requires significantly less + computing resources and storages" + homepage: "https://github.com/fenderglass/Flye" + documentation: "https://nextdenovo.readthedocs.io/en/latest/" + tool_dev_url: "https://github.com/Nextomics/NextDenovo" + doi: "10.1186/s13059-024-03252-4" + licence: ["GPL-3.0-license"] + identifier: biotools:nextdenovo +input: + - - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test' ] + - reads: + type: file + description: Input reads from Oxford Nanopore or PacBio data in FASTA/FASTQ + format. + pattern: "*.{fasta,fastq,fasta.gz,fastq.gz,fa,fq,fa.gz,fq.gz}" + - - config: + type: file + description: Input config file for nextDenovo + pattern: "*" +output: + - fasta: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test' ] + - "*.fasta.gz": + type: file + description: Assembled FASTA file + pattern: "*.fasta.gz" + - stat: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test' ] + - "*.stat": + type: file + description: Extra information and statistics about resulting contigs + pattern: "*.stat" + - versions: + - versions.yml: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@elmedjadjirayane" +maintainers: + - "@elmedjadjirayane" diff --git a/modules/nf-core/nextdenovo/tests/config.cfg b/modules/nf-core/nextdenovo/tests/config.cfg new file mode 100644 index 00000000000..48415b10919 --- /dev/null +++ b/modules/nf-core/nextdenovo/tests/config.cfg @@ -0,0 +1,25 @@ +[General] +job_type = local # local, slurm, sge, pbs, lsf +job_prefix = nextDenovo +task = all # all, correct, assemble +rewrite = yes # yes/no +deltmp = yes +parallel_jobs = 20 # number of tasks used to run in parallel +input_type = raw # raw, corrected +read_type = ont # clr, ont, hifi +input_fofn = input.fofn +workdir = . + +[correct_option] +read_cutoff = 500 +genome_size = 100k # estimated genome size + +minimap2_options_raw = -t 8 +pa_correction = 3 # number of corrected tasks used to run in parallel, each corrected task requires ~TOTAL_INPUT_BASES/4 bytes of memory usage. +correction_options = -p 15 + +[assemble_option] +minimap2_options_cns = -t 8 +nextgraph_options = -a 1 -z 1 -l 1 -q 0 -N 2 -u 2 -w 3 -B 50 -C 5 -L 1 -t 50 + +# see https://nextdenovo.readthedocs.io/en/latest/OPTION.html for a detailed introduction about all the parameters diff --git a/modules/nf-core/nextdenovo/tests/main.nf.test b/modules/nf-core/nextdenovo/tests/main.nf.test new file mode 100644 index 00000000000..fc6c9204bbd --- /dev/null +++ b/modules/nf-core/nextdenovo/tests/main.nf.test @@ -0,0 +1,45 @@ +// nf-core modules test nextdenovo +nextflow_process { + + name "Test Process NEXTDENOVO" + script "../main.nf" + process "NEXTDENOVO" + + tag "modules" + tag "modules_nfcore" + tag "nextdenovo" + + + test("nextdenovo_ont") { + + + when { + process { + """ + + + input[0] = [ + [ id:'test' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/pacbio/fastq/test_hifi.fastq.gz', checkIfExists: true), + ] + input[1] = file("${moduleDir}/tests/config.cfg") + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + file(process.out.fasta.get(0).get(1)).name, + path(process.out.stat.get(0).get(1)).readLines()[1].contains("N50"), + process.out.versions + ).match() } + ) + } + + } + + + +} diff --git a/modules/nf-core/nextdenovo/tests/main.nf.test.snap b/modules/nf-core/nextdenovo/tests/main.nf.test.snap new file mode 100644 index 00000000000..16b601aea6b --- /dev/null +++ b/modules/nf-core/nextdenovo/tests/main.nf.test.snap @@ -0,0 +1,16 @@ +{ + "nextdenovo_ont": { + "content": [ + "test.assembly.fasta.gz", + false, + [ + "versions.yml:md5,7ec3ec49cbe9e0a06d3d0be767e4cc0c" + ] + ], + "meta": { + "nf-test": "0.9.2", + "nextflow": "25.04.2" + }, + "timestamp": "2025-05-16T18:13:58.045501794" + } +} \ No newline at end of file