diff --git a/CHANGELOG.md b/CHANGELOG.md index bbf061d7..f6d1882a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets now require a `db_type` column to distinguish between short- and long-read databases (added by @LilyAnderssonLee) - [#505](https://github.com/nf-core/taxprofiler/pull/505) - Add small files to the file `tower.yml` (added by @LilyAnderssonLee) - [#508](https://github.com/nf-core/taxprofiler/pull/508) - Add `nanoq` as a filtering tool for nanopore reads (added by @LilyAnderssonLee) +- [#511](https://github.com/nf-core/taxprofiler/pull/511) - Add `porechop_abi` as an alternative adapter removal tool for long reads nanopore data (added by @LilyAnderssonLee) ### `Fixed` diff --git a/CITATIONS.md b/CITATIONS.md index 36456b25..9079373f 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -38,6 +38,10 @@ > Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. https://doi.org/10.1099/mgen.0.000132 +- [Porechop_ABI](https://github.com/bonsai-team/Porechop_ABI) + + > Bonenfant, Q., Noé, L., & Touzet, H. (2023). Porechop_ABI: discovering unknown adapters in Oxford Nanopore Technology sequencing reads for downstream trimming. Bioinformatics Advances, 3(1):vbac085. https://10.1093/bioadv/vbac085 + - [Filtlong](https://github.com/rrwick/Filtlong) > Wick R (2021) Filtlong, URL: https://github.com/rrwick/Filtlong diff --git a/README.md b/README.md index d87c5f63..a3edf867 100644 --- a/README.md +++ b/README.md @@ -29,7 +29,7 @@ 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) or [`falco`](https://github.com/smithlabcode/falco) as an alternative option) 2. Performs optional read pre-processing - - Adapter clipping and merging (short-read: [fastp](https://github.com/OpenGene/fastp), [AdapterRemoval2](https://github.com/MikkelSchubert/adapterremoval); long-read: [porechop](https://github.com/rrwick/Porechop)) + - Adapter clipping and merging (short-read: [fastp](https://github.com/OpenGene/fastp), [AdapterRemoval2](https://github.com/MikkelSchubert/adapterremoval); long-read: [porechop](https://github.com/rrwick/Porechop), [Porechop_ABI](https://github.com/bonsai-team/Porechop_ABI)) - Low complexity and quality filtering (short-read: [bbduk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/), [PRINSEQ++](https://github.com/Adrian-Cantu/PRINSEQ-plus-plus); long-read: [Filtlong](https://github.com/rrwick/Filtlong)), [Nanoq](https://github.com/esteinig/nanoq) - Host-read removal (short-read: [BowTie2](http://bowtie-bio.sourceforge.net/bowtie2/); long-read: [Minimap2](https://github.com/lh3/minimap2)) - Run merging diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 087099ba..6f1bfa10 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -25,6 +25,8 @@ report_section_order: order: 500 porechop: order: 400 + porechop_abi: + order: 450 bbduk: order: 300 prinseqplusplus: @@ -106,7 +108,21 @@ top_modules: - "*raw*" extra: "If used in this run, Falco is a drop-in replacement for FastQC producing the same output, written by Guilherme de Sena Brandine and Andrew D. Smith." - "porechop": + name: "Porechop" + anchor: "porechop" + target: "Porechop" + path_filters: + - "*porechop.log" extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop did not detect any adapters and therefore no statistics generated." + - "porechop": + name: "Porechop_ABI" + anchor: "porechop_abi" + target: "Porechop_ABI" + doi: "10.1093/bioadv/vbac085" + info: "find and remove adapters from Oxford Nanopore reads." + path_filters: + - "*porechop_abi.log" + extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop_abi did not detect any adapters and therefore no statistics generated." - "bowtie2": name: "bowtie2" - "samtools": @@ -177,6 +193,14 @@ table_columns_placement: End Trimmed Percent: 440 Middle Split: 450 Middle Split Percent: 460 + Porechop_ABI: + Input Reads: 400 + Start Trimmed: 410 + Start Trimmed Percent: 420 + End Trimmed: 430 + End Trimmed Percent: 440 + Middle Split: 450 + Middle Split Percent: 460 Filtlong: Target bases: 500 BBDuk: @@ -250,6 +274,14 @@ table_columns_visible: End Trimmed Percent: True Middle Split: False Middle Split Percent: True + porechop_abi: + Input reads: False + Start Trimmed: + Start Trimmed Percent: True + End Trimmed: False + End Trimmed Percent: True + Middle Split: False + Middle Split Percent: True fastp: pct_adapter: True pct_surviving: True @@ -315,6 +347,8 @@ extra_fn_clean_exts: - ".bbduk" - ".unmapped" - "_filtered" + - "porechop" + - "porechop_abi" - type: remove pattern: "_falco" diff --git a/conf/modules.config b/conf/modules.config index 22e9fd0a..2252b57f 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -241,12 +241,12 @@ process { } withName: PORECHOP_PORECHOP { - ext.prefix = { "${meta.id}_${meta.run_accession}" } + ext.prefix = { "${meta.id}_${meta.run_accession}_porechop" } publishDir = [ [ path: { "${params.outdir}/porechop" }, mode: params.publish_dir_mode, - pattern: '*_porechopped.fastq.gz', + pattern: '*.fastq.gz', enabled: params.save_preprocessed_reads ], [ @@ -257,7 +257,31 @@ process { [ path: { "${params.outdir}/analysis_ready_fastqs" }, mode: params.publish_dir_mode, - pattern: '*_porechopped.fastq.gz', + pattern: '*.fastq.gz', + enabled: params.save_analysis_ready_fastqs, + saveAs: { ( params.perform_runmerging == false || ( params.perform_runmerging && !meta.is_multirun ) ) && !params.perform_longread_hostremoval && params.longread_qc_skipqualityfilter && !params.longread_qc_skipadaptertrim && params.perform_longread_qc && params.save_analysis_ready_fastqs ? it : null } + ] + ] + } + + withName: PORECHOP_ABI { + ext.prefix = { "${meta.id}_${meta.run_accession}_porechop_abi" } + publishDir = [ + [ + path: { "${params.outdir}/porechop_abi" }, + mode: params.publish_dir_mode, + pattern: '*.fastq.gz', + enabled: params.save_preprocessed_reads + ], + [ + path: { "${params.outdir}/porechop_abi" }, + mode: params.publish_dir_mode, + pattern: '*.log' + ], + [ + path: { "${params.outdir}/analysis_ready_fastqs" }, + mode: params.publish_dir_mode, + pattern: '*.fastq.gz', enabled: params.save_analysis_ready_fastqs, saveAs: { ( params.perform_runmerging == false || ( params.perform_runmerging && !meta.is_multirun ) ) && !params.perform_longread_hostremoval && params.longread_qc_skipqualityfilter && !params.longread_qc_skipadaptertrim && params.perform_longread_qc && params.save_analysis_ready_fastqs ? it : null } ] diff --git a/docs/output.md b/docs/output.md index 6cecb839..285c4ec1 100644 --- a/docs/output.md +++ b/docs/output.md @@ -16,6 +16,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d - [fastp](#fastp) - Adapter trimming for Illumina data - [AdapterRemoval](#adapterremoval) - Adapter trimming for Illumina data - [Porechop](#porechop) - Adapter removal for Oxford Nanopore data +- [Porechop_ABI](#porechop_abi) - Adapter removal for Oxford Nanopore data - [Nonpareil](#nonpareil) - Read redundancy and metagenome coverage estimation for short reads - [BBDuk](#bbduk) - Quality trimming and filtering for Illumina data - [PRINSEQ++](#prinseq) - Quality trimming and filtering for Illunina data @@ -178,6 +179,23 @@ You will only find the `.fastq` files in the results directory if you provide ` We do **not** recommend using Porechop if you are already trimming the adapters with ONT's basecaller Guppy. ::: +### Porechop_ABI + +[Porechop_ABI](https://github.com/bonsai-team/Porechop_ABI) is an extension of [Porechop](https://github.com/rrwick/Porechop). Porechop_ABI does not use any external knowledge or database for the adapters. Adapters are discovered directly from the reads using approximate k-mers counting and assembly. Then these sequences can be used for trimming, using all standard Porechop options. The software is able to report a combination of distinct sequences if a mix of adapters is used. It can also be used to check whether a dataset has already been trimmed out or not, or to find leftover adapters in datasets that have been previously processed with Guppy. + +
+Output files + +- `porechop_abi/` + - `.log`: Log file containing trimming statistics + - `.fastq.gz`: Adapter-trimmed file + +
+ +The output logs are saved in the output folder and are part of MultiQC report.You do not normally need to check these manually. + +You will only find the `.fastq` files in the results directory if you provide ` --save_preprocessed_reads`. Alternatively, if you wish only to have the 'final' reads that go into classification/profiling (i.e., that may have additional processing), do not specify this flag but rather specify `--save_analysis_ready_reads`, in which case the reads will be in the folder `analysis_ready_reads`. + ### BBDuk [BBDuk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/bbduk-guide/) stands for Decontamination Using Kmers. BBDuk was developed to combine most common data-quality-related trimming, filtering, and masking operations into a single high-performance tool. diff --git a/docs/usage.md b/docs/usage.md index 4f1939e3..c6294bd9 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -252,7 +252,7 @@ By default, paired-end merging is not activated. In this case paired-end 'alignm You can also turn off clipping and only perform paired-end merging, if requested. This can be useful when processing data downloaded from the ENA, SRA, or DDBJ (`--shortread_qc_skipadaptertrim`). Both tools support length filtering of reads and can be tuned with `--shortread_qc_minlength`. Performing length filtering can be useful to remove short (often low sequencing complexity) sequences that result in unspecific classification and therefore slow down runtime during classification/profiling, with minimal gain. -There is currently one option for long-read Oxford Nanopore processing: [`porechop`](https://github.com/rrwick/Porechop). +There are currently two options for long-read Oxford Nanopore processing: [`porechop`](https://github.com/rrwick/Porechop), [`porechop_abi`](https://github.com/bonsai-team/Porechop_ABI). For both short-read and long-read preprocessing, you can optionally save the resulting processed reads with `--save_preprocessed_reads`. diff --git a/modules.json b/modules.json index d72d4e3d..47792ee0 100644 --- a/modules.json +++ b/modules.json @@ -215,6 +215,12 @@ "git_sha": "729335dda8ba226323edc54dec80ae959079207e", "installed_by": ["modules"] }, + "porechop/abi": { + "branch": "master", + "git_sha": "870f9af2eaf0000c94d74910d762cf153752af98", + "installed_by": ["modules"], + "patch": "modules/nf-core/porechop/abi/porechop-abi.diff" + }, "porechop/porechop": { "branch": "master", "git_sha": "911696ea0b62df80e900ef244d7867d177971f73", diff --git a/modules/nf-core/porechop/abi/environment.yml b/modules/nf-core/porechop/abi/environment.yml new file mode 100644 index 00000000..4dd2eab1 --- /dev/null +++ b/modules/nf-core/porechop/abi/environment.yml @@ -0,0 +1,9 @@ +--- +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json +name: porechop_abi +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - bioconda::porechop_abi=0.5.0 diff --git a/modules/nf-core/porechop/abi/main.nf b/modules/nf-core/porechop/abi/main.nf new file mode 100644 index 00000000..e9fa9e91 --- /dev/null +++ b/modules/nf-core/porechop/abi/main.nf @@ -0,0 +1,55 @@ +process PORECHOP_ABI { + tag "$meta.id" + label 'process_medium' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/porechop_abi:0.5.0--py310h590eda1_0': + 'biocontainers/porechop_abi:0.5.0--py310h590eda1_0' }" + + input: + tuple val(meta), path(reads) + + output: + tuple val(meta), path("*.fastq.gz") , emit: reads + tuple val(meta), path("*.log") , emit: log + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}.porechop_abi" + if ("$reads" == "${prefix}.fastq.gz") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!" + + """ + ## To ensure ID matches rest of pipeline based on meta.id rather than input file name + + [[ -f ${prefix}.fastq.gz ]] || ln -s $reads ${prefix}.fastq.gz + + porechop_abi \\ + --input ${prefix}.fastq.gz \\ + --threads $task.cpus \\ + $args \\ + --output ${prefix}.fastq.gz \\ + | tee ${prefix}.log + cat <<-END_VERSIONS > versions.yml + "${task.process}": + porechop_abi: \$( porechop_abi --version ) + END_VERSIONS + """ + + stub: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}.porechop_abi" + """ + echo "" | gzip > ${prefix}.fastq.gz + touch ${prefix}.log + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + porechop_abi: \$( porechop_abi --version ) + END_VERSIONS + """ +} diff --git a/modules/nf-core/porechop/abi/meta.yml b/modules/nf-core/porechop/abi/meta.yml new file mode 100644 index 00000000..a856ffbe --- /dev/null +++ b/modules/nf-core/porechop/abi/meta.yml @@ -0,0 +1,48 @@ +name: "porechop_abi" +description: Extension of Porechop whose purpose is to process adapter sequences in ONT reads. +keywords: + - porechop_abi + - adapter + - nanopore +tools: + - "porechop_abi": + description: Extension of Porechop whose purpose is to process adapter sequences in ONT reads. + homepage: "https://github.com/bonsai-team/Porechop_ABI" + documentation: "https://github.com/bonsai-team/Porechop_ABI" + tool_dev_url: "https://github.com/bonsai-team/Porechop_ABI" + doi: "10.1101/2022.07.07.499093" + licence: ["MIT"] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - reads: + type: file + description: fastq/fastq.gz file + pattern: "*.{fastq,fastq.gz,fq,fq.gz}" +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: Adapter-trimmed fastq.gz file + pattern: "*.fastq.gz" + - log: + type: file + description: Log file containing stdout information + pattern: "*.log" +authors: + - "@sofstam" + - "LilyAnderssonLee" +maintainers: + - "@sofstam" + - "LilyAnderssonLee" diff --git a/modules/nf-core/porechop/abi/porechop-abi.diff b/modules/nf-core/porechop/abi/porechop-abi.diff new file mode 100644 index 00000000..4aee2e91 --- /dev/null +++ b/modules/nf-core/porechop/abi/porechop-abi.diff @@ -0,0 +1,21 @@ +Changes in module 'nf-core/porechop/abi' +--- modules/nf-core/porechop/abi/main.nf ++++ modules/nf-core/porechop/abi/main.nf +@@ -22,9 +22,14 @@ + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}.porechop_abi" + if ("$reads" == "${prefix}.fastq.gz") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!" ++ + """ ++ ## To ensure ID matches rest of pipeline based on meta.id rather than input file name ++ ++ [[ -f ${prefix}.fastq.gz ]] || ln -s $reads ${prefix}.fastq.gz ++ + porechop_abi \\ +- --input $reads \\ ++ --input ${prefix}.fastq.gz \\ + --threads $task.cpus \\ + $args \\ + --output ${prefix}.fastq.gz \\ + +************************************************************ diff --git a/modules/nf-core/porechop/abi/tests/main.nf.test b/modules/nf-core/porechop/abi/tests/main.nf.test new file mode 100644 index 00000000..b5a29f90 --- /dev/null +++ b/modules/nf-core/porechop/abi/tests/main.nf.test @@ -0,0 +1,59 @@ +nextflow_process { + + name "Test Process PORECHOP_ABI" + script "../main.nf" + process "PORECHOP_ABI" + tag "modules" + tag "modules_nfcore" + tag "porechop" + tag "porechop/abi" + + test("sarscov2-nanopore") { + + when { + process { + """ + input[0] = [ + [ id:'test'], // meta map + file(params.modules_testdata_base_path + 'genomics/sarscov2/nanopore/fastq/test.fastq.gz', checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.reads, + file(process.out.log.get(0).get(1)).readLines()[20..40], + process.out.versions).match() + } + ) + } + } + + test("sarscov2-nanopore - stub") { + + options "-stub" + + when { + + process { + """ + input[0] = [ + [ id:'test'], // meta map + file(params.modules_testdata_base_path + 'genomics/sarscov2/nanopore/fastq/test.fastq.gz', checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } +} diff --git a/modules/nf-core/porechop/abi/tests/main.nf.test.snap b/modules/nf-core/porechop/abi/tests/main.nf.test.snap new file mode 100644 index 00000000..ad63f4ed --- /dev/null +++ b/modules/nf-core/porechop/abi/tests/main.nf.test.snap @@ -0,0 +1,94 @@ +{ + "sarscov2-nanopore": { + "content": [ + [ + [ + { + "id": "test" + }, + "test.porechop_abi.fastq.gz:md5,886fdb859fb50e0dddd35007bcff043e" + ] + ], + [ + " Best \u001b[0m", + " read Best \u001b[0m", + " start read end\u001b[0m", + " \u001b[4mSet %ID %ID \u001b[0m", + " \u001b[32mSQK-NSK007 100.0 73.1\u001b[0m", + " Rapid 40.4 0.0", + " RBK004_upstream 77.5 0.0", + " SQK-MAP006 75.8 72.7", + " SQK-MAP006 short 65.5 66.7", + " PCR adapters 1 73.9 69.6", + " PCR adapters 2 80.0 72.7", + " PCR adapters 3 70.8 69.6", + " 1D^2 part 1 71.4 70.0", + " 1D^2 part 2 84.8 75.8", + " cDNA SSP 63.0 61.7", + " \u001b[32mBarcode 1 (reverse) 100.0 100.0\u001b[0m", + " Barcode 2 (reverse) 70.8 69.2", + " Barcode 3 (reverse) 76.0 70.4", + " Barcode 4 (reverse) 74.1 71.4", + " Barcode 5 (reverse) 77.8 80.8", + " Barcode 6 (reverse) 73.1 70.8" + ], + [ + "versions.yml:md5,0e9e5e0d35a68ff8e6490c949b257f98" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.04.1" + }, + "timestamp": "2024-07-29T13:50:49.318599" + }, + "sarscov2-nanopore - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test" + }, + "test.porechop_abi.fastq.gz:md5,68b329da9893e34099c7d8ad5cb9c940" + ] + ], + "1": [ + [ + { + "id": "test" + }, + "test.porechop_abi.log:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "2": [ + "versions.yml:md5,0e9e5e0d35a68ff8e6490c949b257f98" + ], + "log": [ + [ + { + "id": "test" + }, + "test.porechop_abi.log:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "reads": [ + [ + { + "id": "test" + }, + "test.porechop_abi.fastq.gz:md5,68b329da9893e34099c7d8ad5cb9c940" + ] + ], + "versions": [ + "versions.yml:md5,0e9e5e0d35a68ff8e6490c949b257f98" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.04.1" + }, + "timestamp": "2024-07-29T13:50:54.425389" + } +} \ No newline at end of file diff --git a/modules/nf-core/porechop/abi/tests/tags.yml b/modules/nf-core/porechop/abi/tests/tags.yml new file mode 100644 index 00000000..e19350cd --- /dev/null +++ b/modules/nf-core/porechop/abi/tests/tags.yml @@ -0,0 +1,2 @@ +porechop/abi: + - "modules/nf-core/porechop/abi/**" diff --git a/nextflow.config b/nextflow.config index 3903aa4c..8c763bcf 100644 --- a/nextflow.config +++ b/nextflow.config @@ -79,7 +79,7 @@ params { shortread_qc_dedup = false perform_longread_qc = false - longread_adapterremoval_tool = 'porechop' + longread_adapterremoval_tool = 'porechop_abi' longread_qc_skipadaptertrim = false longread_qc_skipqualityfilter = false longread_filter_tool = 'nanoq' diff --git a/nextflow_schema.json b/nextflow_schema.json index e2c13e7c..b43cefcb 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -240,10 +240,11 @@ }, "longread_adapterremoval_tool": { "type": "string", - "default": "porechop", - "enum": ["porechop"], + "default": "porechop_abi", + "enum": ["porechop", "porechop_abi"], "fa_icon": "fas fa-hammer", - "description": "Specify which tool to use for adapter trimming. Currently only one option." + "description": "Specify which tool to use for adapter trimming.", + "help_text": "The performance of Porechop and Porechop_ABI is same in terms of removing adapter reads. However Porechop is no longer updated, Porechop_ABI receives regular updates." }, "longread_qc_skipadaptertrim": { "type": "boolean", diff --git a/subworkflows/local/longread_adapterremoval.nf b/subworkflows/local/longread_adapterremoval.nf index 3e2ffcc4..f32bf8d1 100644 --- a/subworkflows/local/longread_adapterremoval.nf +++ b/subworkflows/local/longread_adapterremoval.nf @@ -3,6 +3,7 @@ // include { PORECHOP_PORECHOP } from '../../modules/nf-core/porechop/porechop/main' +include { PORECHOP_ABI } from '../../modules/nf-core/porechop/abi/main' workflow LONGREAD_ADAPTERREMOVAL { take: @@ -12,7 +13,13 @@ workflow LONGREAD_ADAPTERREMOVAL { ch_versions = Channel.empty() ch_multiqc_files = Channel.empty() - if (params.longread_adapterremoval_tool == 'porechop') { + if (params.longread_adapterremoval_tool == 'porechop_abi') { + PORECHOP_ABI (reads) + ch_processed_reads = PORECHOP_ABI.out.reads + .map { meta, reads -> [meta + [ single_end: true ], reads ] } + ch_versions = ch_versions.mix( PORECHOP_ABI.out.versions.first() ) + ch_multiqc_files = ch_multiqc_files.mix( PORECHOP_ABI.out.log ) + } else if (params.longread_adapterremoval_tool == 'porechop') { PORECHOP_PORECHOP ( reads ) ch_processed_reads = PORECHOP_PORECHOP.out.reads .map { meta, reads -> [ meta + [single_end: true], reads ] } diff --git a/subworkflows/local/longread_preprocessing.nf b/subworkflows/local/longread_preprocessing.nf index c35e0c1f..3b25879d 100644 --- a/subworkflows/local/longread_preprocessing.nf +++ b/subworkflows/local/longread_preprocessing.nf @@ -1,5 +1,5 @@ // -// Process long raw reads with porechop +// Perform read trimming and filtering // include { FASTQC as FASTQC_PROCESSED } from '../../modules/nf-core/fastqc/main' diff --git a/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf b/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf index 1e3d08c3..b6e8c305 100644 --- a/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf +++ b/subworkflows/local/utils_nfcore_taxprofiler_pipeline/main.nf @@ -210,9 +210,10 @@ def toolCitationText() { def text_longread_qc = [ "Long read preprocessing was performed with:", - !params.longread_qc_skipadaptertrim ? "Porechop (Wick et al. 2017)," : "", - params.longread_filter_tool == "filtlong" ? "Filtlong (Wick 2021)," : "", - params.longread_filter_tool == "nanoq" ? "Nanoq (Steinig and Coin 2022)," : "", + params.longread_adapterremoval_tool == "porechop_abi" ? "Porechop_ABI (Bonenfant et al. 2023)." : "", + params.longread_adapterremoval_tool == "porechop" ? "Porechop (Wick et al. 2017)." : "", + params.longread_filter_tool == "filtlong" ? "Filtlong (Wick 2021)." : "", + params.longread_filter_tool == "nanoq" ? "Nanoq (Steinig and Coin 2022)." : "", ].join(' ').trim() def text_shortreadcomplexity = [ @@ -289,7 +290,8 @@ def toolBibliographyText() { ].join(' ').trim() def text_longread_qc = [ - !params.longread_qc_skipadaptertrim ? "
  • Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. 10.1099/mgen.0.000132
    • " : "", + params.longread_adapterremoval_tool == "porechop_abi" ? "
  • Bonenfant, Q., Noé, L., & Touzet, H. (2023). Porechop_ABI: discovering unknown adapters in Oxford Nanopore Technology sequencing reads for downstream trimming. Bioinformatics Advances, 3(1):vbac085. 10.1093/bioadv/vbac085
    • " : "", + params.longread_adapterremoval_tool == "porechop" ? "
  • Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. 10.1099/mgen.0.000132
    • " : "", params.longread_filter_tool == "filtlong" ? "
  • Wick R. (2021) Filtlong, URL: https://github.com/rrwick/Filtlong
    • " : "", params.longread_filter_tool == "nanoq" ? "
  • Steinig, E., & Coin, L. (2022). Nanoq: ultra-fast quality control for nanopore reads. Journal of Open Source Software, 7(69). 10.21105/joss.02991
    • " : "" ].join(' ').trim() diff --git a/subworkflows/local/visualization_krona.nf b/subworkflows/local/visualization_krona.nf index 77e26a22..eb9b6cf6 100644 --- a/subworkflows/local/visualization_krona.nf +++ b/subworkflows/local/visualization_krona.nf @@ -99,6 +99,7 @@ workflow VISUALIZATION_KRONA { KRONA_KTIMPORTTAXONOMY ( ch_krona_taxonomy_for_input, file(params.krona_taxonomy_directory, checkExists: true) ) ch_krona_html.mix( KRONA_KTIMPORTTAXONOMY.out.html ) + ch_versions = ch_versions.mix ( GUNZIP.out.versions.first() ) ch_versions = ch_versions.mix( MEGAN_RMA2INFO_KRONA.out.versions.first() ) ch_versions = ch_versions.mix( KRONA_KTIMPORTTAXONOMY.out.versions.first() ) }