From 1fe5c94f41933958c73f04b96a5eb864b8bc6e5c Mon Sep 17 00:00:00 2001 From: sainsachiko Date: Fri, 15 May 2026 13:20:15 +0100 Subject: [PATCH 1/7] Handle empty barcode --- assets/samplesheet.csv | 2 +- docs/usage.md | 15 ++++++++------- subworkflows/local/align_long.nf | 11 +++++++---- tests/default.nf.test.snap | 20 ++++++++++---------- 4 files changed, 26 insertions(+), 22 deletions(-) diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv index ec1c7289..b742ba18 100644 --- a/assets/samplesheet.csv +++ b/assets/samplesheet.csv @@ -4,5 +4,5 @@ SAMEA7524439,ERR6688600,illumina,https://tolit.cog.sanger.ac.uk/test-data/Meles_ SAMEA7524440,ERR6688402,hic,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/genomic_data/mMelMel3/hic/35528_2_1.subset.cram,, SAMEA7524440,PAE35587,ont,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/genomic_data/mMelMel3/ont/PAE35587_pass_1f1f0707_115.subset.fastq.gz,, SAMEA7524440,PAE35587_test,ont,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/genomic_data/mMelMel3/ont/PAE35587_pass_1f1f0707_115.subset.addrg.bam,, -SAMEA7524440,ERR6939248,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/genomic_data/mMelMel3/pacbio/m64094_200910_173211.ccs.bc1022_BAK8B_OA--bc1022_BAK8B_OA.subset.bam,,bc1022 +SAMEA7524440,ERR6939248,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/genomic_data/mMelMel3/pacbio/m64094_200910_173211.ccs.bc1022_BAK8B_OA--bc1022_BAK8B_OA.subset.bam,, SAMEA7524440,ERR6939249,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Meles_meles/genomic_data/mMelMel3/pacbio/m64094_200911_174739.ccs.bc1022_BAK8B_OA--bc1022_BAK8B_OA.subset.fastq.gz,,bc1022 diff --git a/docs/usage.md b/docs/usage.md index 9f83acbe..1cf4fbb7 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -8,7 +8,7 @@ This pipeline aligns raw reads from various technolgies (such as HiC, Illumina, ## Samplesheet input -You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 4 columns, and a header row as shown in the examples below. +You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 6 columns, and a header row as shown in the examples below. ```bash --input '[path to samplesheet file]' @@ -32,12 +32,12 @@ The samplesheet can have as many columns as you desire, however, there is a stri A final samplesheet file consisting of both HiC and PacBio data may look something like the one below. ```console -specimen,run,datatype,datafile,library -specimen1,run1,hic1.cram, -specimen1,run2,hic2.cram, -specimen2,run3,hic3.cram, -specimen2,run4,pacbio,pacbio1.bam,uli -specimen3,run5,pacbio,pacbio2.bam, +specimen,run,datatype,datafile,library,barcode +specimen1,run1,hic1.cram,, +specimen1,run2,hic2.cram,, +specimen2,run3,hic3.cram,, +specimen2,run4,pacbio,pacbio1.bam,uli, +specimen3,run5,pacbio,pacbio2.bam,, ``` | Column | Description | @@ -47,6 +47,7 @@ specimen3,run5,pacbio,pacbio2.bam, | `datatype` | Type of sequencing data. Must be one of `hic`, `illumina`, `pacbio`, `pacbio_clr`, or `ont`. | | `datafile` | Full path to read data file. Must be `bam`, `cram`, `fastq.gz` or `fq.gz` for `illumina` and `hic`. Must be `bam`, `fastq.gz` or `fq.gz` for `pacbio`, `pacbio_clr`, and `ont`. Note that FASTQ inputs should be interleaved if paired-end. | | `library` | (Optional) The library value is a unique identifier which is assigned to read group (`@RG`) ID. If the library name is not specified, the pipeline will auto-create library name using the data filename provided in the samplesheet. | +| `barcode` | (Optional) Barcode identifier used to trim barcode adapater for PacBio reads | An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. diff --git a/subworkflows/local/align_long.nf b/subworkflows/local/align_long.nf index ec00f872..2f3a8c8f 100644 --- a/subworkflows/local/align_long.nf +++ b/subworkflows/local/align_long.nf @@ -83,11 +83,14 @@ workflow ALIGN_LONG { if (val_pacbio_adapter_fasta && val_pacbio_adapter_yaml) { ch_yaml_meta = ch_reads.pacbio .combine( channel.fromPath(val_pacbio_adapter_yaml, checkIfExists: true) ) - .map { meta, _reads, yaml -> [ meta, yaml ] + .map{ meta, _reads, yaml -> [ meta, yaml ]} + .branch { meta, yaml -> + has_barcode: meta.barcode != null && !meta.barcode.isEmpty() + no_barcode: true } - - GAWK_MODIFY_YAML_BARCODE( ch_yaml_meta, [], false ) - ch_pacbio_read_yaml = ch_reads.pacbio.combine(GAWK_MODIFY_YAML_BARCODE.out.output, by: 0) + GAWK_MODIFY_YAML_BARCODE( ch_yaml_meta.has_barcode, [], false ) + ch_yml_barcoded = GAWK_MODIFY_YAML_BARCODE.out.output.mix( ch_yaml_meta.no_barcode ) + ch_pacbio_read_yaml = ch_reads.pacbio.combine(ch_yml_barcoded, by: 0) adapter_fasta_for_preprocess = [[id:file( val_pacbio_adapter_fasta ).baseName], val_pacbio_adapter_fasta] } else { ch_pacbio_read_yaml = ch_reads.pacbio.map { meta, read_files -> [ meta, read_files, [] ] } //PacBio reads with dummy yaml diff --git a/tests/default.nf.test.snap b/tests/default.nf.test.snap index 7870b20c..99f9cdc6 100644 --- a/tests/default.nf.test.snap +++ b/tests/default.nf.test.snap @@ -1,7 +1,7 @@ { "-profile test": { "content": [ - 176, + 175, { "BGZIP_BEDGRAPH": { "samtools": "1.23.1" @@ -257,24 +257,24 @@ "GCA_922984935.2.subset.ont.SAMEA7524440.merged_1.minimap2.flagstat:md5,ec6aaeb8be068f8b35a56d091d38c8b0", "GCA_922984935.2.subset.ont.SAMEA7524440.merged_1.minimap2.idxstats:md5,5e872e9487a31f09266c6a73b3dbbd38", "GCA_922984935.2.subset.ont.SAMEA7524440.merged_1.minimap2.stats.gz:md5,b2196feb830687c0f303effdd7a2ad94", - "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939248.minimap2.coverage.1k.bedGraph.gz:md5,5ad4ef58cd155a1b9f56f65ee02e6084", - "pacbio.SAMEA7524440.ERR6939248.hifitrimmer.bed.gz:md5,0fe5fe224b52d743066bb3e03fecd982", + "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939248.minimap2.coverage.1k.bedGraph.gz:md5,f7e99e6b9fa95ba67f7fe1486bcce1f6", + "pacbio.SAMEA7524440.ERR6939248.hifitrimmer.bed.gz:md5,3002179a24e3db9145f57460622eb02f", "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939248.minimap2.flagstat:md5,db1610f3490d314de7e60f10d404178d", "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939248.minimap2.idxstats:md5,f757bd37fc1461e576348525ae0ba087", - "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939248.minimap2.stats.gz:md5,f727dbd990a67c58a91c9c53d0cb6bf2", + "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939248.minimap2.stats.gz:md5,4e1533437cc4fd9c0525150391755520", "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939249.minimap2.coverage.1k.bedGraph.gz:md5,adf81ade1a26064658861318edfb5df1", "pacbio.SAMEA7524440.ERR6939249.hifitrimmer.bed.gz:md5,16e8458843c0a6e1736f19c297088c32", "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939249.minimap2.flagstat:md5,81a2332a3cdcc6b37dd2687d2cc77752", "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939249.minimap2.idxstats:md5,fe8b829d5241701b172cf4ff55cbf4f6", "GCA_922984935.2.subset.pacbio.SAMEA7524440.ERR6939249.minimap2.stats.gz:md5,91cee5cca6ffa7c8c566791f4f514ee8", - "GCA_922984935.2.subset.pacbio.SAMEA7524440.merged_1.minimap2.coverage.1k.bedGraph.gz:md5,c39c1c0a440f49d83722da029b9bcf5f", + "GCA_922984935.2.subset.pacbio.SAMEA7524440.merged_1.minimap2.coverage.1k.bedGraph.gz:md5,1546e51cd6c63db37014daaa518b3cfe", "SOURCE.txt:md5,343a5205e5b93005576ee69a0869dad3", "GCA_922984935.2.subset.pacbio.SAMEA7524440.merged_1.minimap2.flagstat:md5,da9dcde0937f27935637db67c14c9928", "GCA_922984935.2.subset.pacbio.SAMEA7524440.merged_1.minimap2.idxstats:md5,ee312e0f5e6053bc81b737ae5805807f", - "GCA_922984935.2.subset.pacbio.SAMEA7524440.merged_1.minimap2.stats.gz:md5,9ac83c1939cdee8e020cfba523c89f33" + "GCA_922984935.2.subset.pacbio.SAMEA7524440.merged_1.minimap2.stats.gz:md5,d0afecc3b0dc7c3dda2fb8684c5cec7a" ], { - + }, { "GCA_922984935.2.subset.hic.SAMEA7524440.ERR6688402.bwamem2.cram": { @@ -378,7 +378,7 @@ } }, [ - "pacbio.SAMEA7524440.ERR6939248.hifitrimmer.summary.json:md5,81572321148a5e77738af902fa5f9e71", + "pacbio.SAMEA7524440.ERR6939248.hifitrimmer.summary.json:md5,d2d4198c3f7086437249909d94173359", "pacbio.SAMEA7524440.ERR6939249.hifitrimmer.summary.json:md5,83d9985a6d7a4477df704d8f4a23852c" ] ], @@ -386,6 +386,6 @@ "nf-test": "0.9.3", "nextflow": "25.10.4" }, - "timestamp": "2026-04-29T19:29:08.956210749" + "timestamp": "2026-05-15T12:13:39.841579495" } -} +} \ No newline at end of file From 1672b8048fd698bbbd3c56666ffd04fa177126da Mon Sep 17 00:00:00 2001 From: Hanh Hoang <134130358+sainsachiko@users.noreply.github.com> Date: Fri, 15 May 2026 13:32:11 +0100 Subject: [PATCH 2/7] Fix typo Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- docs/usage.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/usage.md b/docs/usage.md index 1cf4fbb7..10e2335e 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -47,7 +47,7 @@ specimen3,run5,pacbio,pacbio2.bam,, | `datatype` | Type of sequencing data. Must be one of `hic`, `illumina`, `pacbio`, `pacbio_clr`, or `ont`. | | `datafile` | Full path to read data file. Must be `bam`, `cram`, `fastq.gz` or `fq.gz` for `illumina` and `hic`. Must be `bam`, `fastq.gz` or `fq.gz` for `pacbio`, `pacbio_clr`, and `ont`. Note that FASTQ inputs should be interleaved if paired-end. | | `library` | (Optional) The library value is a unique identifier which is assigned to read group (`@RG`) ID. If the library name is not specified, the pipeline will auto-create library name using the data filename provided in the samplesheet. | -| `barcode` | (Optional) Barcode identifier used to trim barcode adapater for PacBio reads | +| `barcode` | (Optional) Barcode identifier used to trim barcode adapter for PacBio reads | An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. From 15cb3beb851bf416e53f47e741f18faeb14ef1a1 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Fri, 15 May 2026 12:46:33 +0000 Subject: [PATCH 3/7] Clarify optional samplesheet columns in usage docs Agent-Logs-Url: https://github.com/sanger-tol/readmapping/sessions/a61689a5-a2a7-402a-bd52-58075aec1701 Co-authored-by: sainsachiko <134130358+sainsachiko@users.noreply.github.com> --- docs/usage.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/usage.md b/docs/usage.md index 10e2335e..7abb8b78 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -8,7 +8,7 @@ This pipeline aligns raw reads from various technolgies (such as HiC, Illumina, ## Samplesheet input -You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 6 columns, and a header row as shown in the examples below. +You will need to create a samplesheet with information about the samples you would like to analyse before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with a header row as shown in the examples below. The first 4 columns are required (`specimen`, `run`, `datatype`, `datafile`), while `library` and `barcode` are optional. ```bash --input '[path to samplesheet file]' @@ -33,9 +33,9 @@ A final samplesheet file consisting of both HiC and PacBio data may look somethi ```console specimen,run,datatype,datafile,library,barcode -specimen1,run1,hic1.cram,, -specimen1,run2,hic2.cram,, -specimen2,run3,hic3.cram,, +specimen1,run1,hic,hic1.cram,, +specimen1,run2,hic,hic2.cram,, +specimen2,run3,hic,hic3.cram,, specimen2,run4,pacbio,pacbio1.bam,uli, specimen3,run5,pacbio,pacbio2.bam,, ``` From 8dfd512484989ab5a4da8454735d1eeab472d305 Mon Sep 17 00:00:00 2001 From: sainsachiko Date: Fri, 15 May 2026 15:53:12 +0100 Subject: [PATCH 4/7] Update description of samplesheet --- docs/usage.md | 2 +- nextflow_schema.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/usage.md b/docs/usage.md index 7abb8b78..8379b8dc 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -47,7 +47,7 @@ specimen3,run5,pacbio,pacbio2.bam,, | `datatype` | Type of sequencing data. Must be one of `hic`, `illumina`, `pacbio`, `pacbio_clr`, or `ont`. | | `datafile` | Full path to read data file. Must be `bam`, `cram`, `fastq.gz` or `fq.gz` for `illumina` and `hic`. Must be `bam`, `fastq.gz` or `fq.gz` for `pacbio`, `pacbio_clr`, and `ont`. Note that FASTQ inputs should be interleaved if paired-end. | | `library` | (Optional) The library value is a unique identifier which is assigned to read group (`@RG`) ID. If the library name is not specified, the pipeline will auto-create library name using the data filename provided in the samplesheet. | -| `barcode` | (Optional) Barcode identifier used to trim barcode adapter for PacBio reads | +| `barcode` | (Optional) Barcode identifier used to trim barcode adapter for PacBio reads. If empty, barcode-specific adapter sequences will not be trimmed. | An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline. diff --git a/nextflow_schema.json b/nextflow_schema.json index 25216f43..167ee87c 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -20,7 +20,7 @@ "mimetype": "text/csv", "pattern": "^\\S+\\.csv$", "description": "Path to comma-separated file containing information about the samples in the experiment.", - "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 4 columns, and a header row.", + "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with at least 4 columns, and a header row.", "fa_icon": "fas fa-file-csv" }, "outdir": { From 5ec9deb2e88de08d97d177dac7b838b3dfe89168 Mon Sep 17 00:00:00 2001 From: sainsachiko Date: Fri, 15 May 2026 15:54:46 +0100 Subject: [PATCH 5/7] Release prep: bump versions, update changelog & release date --- .nf-core.yml | 2 +- CHANGELOG.md | 6 ++++++ CITATION.cff | 6 +++--- nextflow.config | 2 +- ro-crate-metadata.json | 13 +++++++------ tests/default.nf.test.snap | 2 +- tests/short_aligner_minimap2.nf.test.snap | 2 +- tests/uli.nf.test.snap | 2 +- tests/uli_no_lima.nf.test.snap | 2 +- tests/untrim.nf.test.snap | 2 +- 10 files changed, 23 insertions(+), 16 deletions(-) diff --git a/.nf-core.yml b/.nf-core.yml index 5910da29..177a80fe 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -47,4 +47,4 @@ template: - igenomes - multiqc - fastqc - version: 2.0.2 + version: 2.0.3 diff --git a/CHANGELOG.md b/CHANGELOG.md index ba2dc2bc..e2e191b3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,12 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [[v2.0.3](https://github.com/sanger-tol/readmapping/releases/tag/2.0.2)] - Hungarian Horntail (patch 3) - [2026-05-15] + +### Enhancements & fixes + +- Handle empty barcode in the samplesheet + ## [[v2.0.2](https://github.com/sanger-tol/readmapping/releases/tag/2.0.2)] - Hungarian Horntail (patch 2) - [2026-05-07] ### Enhancements & fixes diff --git a/CITATION.cff b/CITATION.cff index b6bc0229..49241964 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -51,13 +51,13 @@ authors: orcid: https://orcid.org/0000-0003-1658-1762 website: https://github.com/BethYates cff-version: 1.2.0 -date-released: "2026-05-07" +date-released: "2026-05-15" doi: 10.5281/zenodo.6563577 license: MIT message: If you use this software, please cite it using the metadata from this file and all references from CITATIONS.md . repository-code: https://github.com/sanger-tol/readmapping -title: sanger-tol/readmapping v2.0.2 - Hungarian Horntail (patch 2) +title: sanger-tol/readmapping v2.0.3 - Hungarian Horntail (patch 2) type: software url: https://pipelines.tol.sanger.ac.uk/readmapping -version: 2.0.2 +version: 2.0.3 diff --git a/nextflow.config b/nextflow.config index f81c1a3a..f43ad01c 100644 --- a/nextflow.config +++ b/nextflow.config @@ -322,7 +322,7 @@ manifest { mainScript = 'main.nf' defaultBranch = 'main' nextflowVersion = '!>=25.04.0' - version = '2.0.2' + version = '2.0.3' doi = '10.5281/zenodo.6563577' } diff --git a/ro-crate-metadata.json b/ro-crate-metadata.json index 7700feb8..2834cc7b 100644 --- a/ro-crate-metadata.json +++ b/ro-crate-metadata.json @@ -1,11 +1,12 @@ { - "@context": "https://w3id.org/ro/crate/1.1/context", + "@context": "https://w3id.org/ro/crate/1.2/context", + "@graph": [ { "@id": "./", "@type": "Dataset", "creativeWorkStatus": "Stable", - "datePublished": "2026-05-07T11:04:49+00:00", + "datePublished": "2026-05-15T14:33:37+00:00", "description": "# sanger-tol/readmapping\n\n![sanger-tol/readmapping](docs/images/sanger-tol-readmapping_logo.png)\n\n[![Open in GitHub Codespaces](https://img.shields.io/badge/Open_In_GitHub_Codespaces-black?labelColor=grey&logo=github)](https://github.com/codespaces/new/sanger-tol/readmapping)\n[![GitHub Actions CI Status](https://github.com/sanger-tol/readmapping/actions/workflows/nf-test.yml/badge.svg)](https://github.com/sanger-tol/readmapping/actions/workflows/nf-test.yml)\n[![GitHub Actions Linting Status](https://github.com/sanger-tol/readmapping/actions/workflows/linting.yml/badge.svg)](https://github.com/sanger-tol/readmapping/actions/workflows/linting.yml)\n[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.6563577-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.6563577)\n[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)\n\n[![Nextflow](https://img.shields.io/badge/version-%E2%89%A525.04.0-green?style=flat&logo=nextflow&logoColor=white&color=%230DC09D&link=https%3A%2F%2Fnextflow.io)](https://www.nextflow.io/)\n[![nf-core template version](https://img.shields.io/badge/nf--core_template-3.5.2-green?style=flat&logo=nfcore&logoColor=white&color=%2324B064&link=https%3A%2F%2Fnf-co.re)](https://github.com/nf-core/tools/releases/tag/3.5.2)\n[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)\n[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)\n[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)\n[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/sanger-tol/readmapping)\n\n## Introduction\n\n**sanger-tol/readmapping** is a bioinformatics best-practice analysis pipeline for mapping reads generated using Illumina, HiC, PacBio and Nanopore technologies against a genome assembly.\n\nThe pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!\n\nOn merge to `dev` and `main` branch, automated continuous integration tests run the pipeline on a full-sized dataset on the Wellcome Sanger Institute HPC farm using the Nextflow Tower infrastructure. This ensures that the pipeline runs on full sized datasets, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources.\n\n## Pipeline summary\n\n\n\n## Quick Start\n\n1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=22.10.1`)\n\n2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/) (you can follow [this tutorial](https://singularity-tutorial.github.io/01-installation/)), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(you can use [`Conda`](https://conda.io/miniconda.html) both to install Nextflow itself and also to manage software within pipelines. Please only use it within pipelines as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_.\n\n3. Download the pipeline and test it on a minimal dataset with a single command:\n\n ```bash\n nextflow run sanger-tol/readmapping -profile test,YOURPROFILE --outdir \n ```\n\n Note that some form of configuration will be needed so that Nextflow knows how to fetch the required software. This is usually done in the form of a config profile (`YOURPROFILE` in the example command above). You can chain multiple config profiles in a comma-separated string.\n\n > - The pipeline comes with config profiles called `docker`, `singularity`, `podman`, `shifter`, `charliecloud` and `conda` which instruct the pipeline to use the named tool for software management. For example, `-profile test,docker`.\n > - Please check [nf-core/configs](https://github.com/nf-core/configs#documentation) to see if a custom config file to run nf-core pipelines already exists for your Institute. If so, you can simply use `-profile ` in your command. This will enable either `docker` or `singularity` and set the appropriate execution settings for your local compute environment.\n > - If you are using `singularity`, please use the [`nf-core download`](https://nf-co.re/tools/#downloading-pipelines-for-offline-use) command to download images first, before running the pipeline. Setting the [`NXF_SINGULARITY_CACHEDIR` or `singularity.cacheDir`](https://www.nextflow.io/docs/latest/singularity.html?#singularity-docker-hub) Nextflow options enables you to store and re-use the images from a central location for future pipeline runs.\n > - If you are using `conda`, it is highly recommended to use the [`NXF_CONDA_CACHEDIR` or `conda.cacheDir`](https://www.nextflow.io/docs/latest/conda.html) settings to store the environments in a central location for future pipeline runs.\n\n4. Start running your own analysis!\n\n ```bash\n nextflow run sanger-tol/readmapping --input samplesheet.csv --fasta genome.fa.gz --outdir -profile \n ```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).\n\n## Credits\n\nsanger-tol/readmapping was originally written by [Priyanka Surana](https://github.com/priyanka-surana).\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\n- [Matthieu Muffato](https://github.com/muffato) for the text logo\n- [Guoying Qi](https://github.com/gq1) for being able to run tests using Nf-Tower and the Sanger HPC farm\n- [Tyler Chafin](https://github.com/tkchafin) for maintenance, updates, and code reviews\n- [Chau Duong](https://github.com/reichan1998) for updates and code reviews\n- [Sandra Babirye](https://github.com/SandraBabirye) for updates and code reviews\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).\n\nFor further information or help, please [create an issue](https://github.com/sanger-tol/readmapping/issues/new/choose) on GitHub if you are not on the Sanger slack channel.\n\n## Citations\n\nIf you use sanger-tol/readmapping for your analysis, please cite it using the following doi: [10.5281/zenodo.6563577](https://doi.org/10.5281/zenodo.6563577)\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nThis pipeline uses code and infrastructure developed and maintained by the [nf-core](https://nf-co.re) community, reused here under the [MIT license](https://github.com/nf-core/tools/blob/main/LICENSE).\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n", "hasPart": [ { @@ -93,7 +94,7 @@ }, "conformsTo": [ { - "@id": "https://w3id.org/ro/crate/1.1" + "@id": "https://w3id.org/ro/crate/1.2" }, { "@id": "https://w3id.org/workflowhub/workflow-ro-crate/1.0" @@ -133,7 +134,7 @@ } ], "dateCreated": "", - "dateModified": "2026-04-29T19:05:01Z", + "dateModified": "2026-05-15T15:33:37Z", "dct:conformsTo": "https://bioschemas.org/profiles/ComputationalWorkflow/1.0-RELEASE/", "keywords": [ "nextflow", @@ -163,10 +164,10 @@ }, "url": [ "https://github.com/sanger-tol/readmapping", - "https://pipelines.tol.sanger.ac.uk/readmapping/2.0.2/" + "https://pipelines.tol.sanger.ac.uk/readmapping/2.0.3/" ], "version": [ - "2.0.2" + "2.0.3" ] }, { diff --git a/tests/default.nf.test.snap b/tests/default.nf.test.snap index 99f9cdc6..8dec181a 100644 --- a/tests/default.nf.test.snap +++ b/tests/default.nf.test.snap @@ -110,7 +110,7 @@ "samtools": "1.23.1" }, "Workflow": { - "sanger-tol/readmapping": "v2.0.2" + "sanger-tol/readmapping": "v2.0.3" } }, [ diff --git a/tests/short_aligner_minimap2.nf.test.snap b/tests/short_aligner_minimap2.nf.test.snap index f0d642ff..f8e9d8b7 100644 --- a/tests/short_aligner_minimap2.nf.test.snap +++ b/tests/short_aligner_minimap2.nf.test.snap @@ -83,7 +83,7 @@ "samtools": "1.23.1" }, "Workflow": { - "sanger-tol/readmapping": "v2.0.2" + "sanger-tol/readmapping": "v2.0.3" } }, [ diff --git a/tests/uli.nf.test.snap b/tests/uli.nf.test.snap index 32962de1..7b8bbf66 100644 --- a/tests/uli.nf.test.snap +++ b/tests/uli.nf.test.snap @@ -85,7 +85,7 @@ "samtools": "1.23.1" }, "Workflow": { - "sanger-tol/readmapping": "v2.0.2" + "sanger-tol/readmapping": "v2.0.3" } }, [ diff --git a/tests/uli_no_lima.nf.test.snap b/tests/uli_no_lima.nf.test.snap index cb2b344e..1e08831b 100644 --- a/tests/uli_no_lima.nf.test.snap +++ b/tests/uli_no_lima.nf.test.snap @@ -82,7 +82,7 @@ "samtools": "1.23.1" }, "Workflow": { - "sanger-tol/readmapping": "v2.0.2" + "sanger-tol/readmapping": "v2.0.3" } }, [ diff --git a/tests/untrim.nf.test.snap b/tests/untrim.nf.test.snap index 7a551266..c85069e7 100644 --- a/tests/untrim.nf.test.snap +++ b/tests/untrim.nf.test.snap @@ -67,7 +67,7 @@ "samtools": "1.23.1" }, "Workflow": { - "sanger-tol/readmapping": "v2.0.2" + "sanger-tol/readmapping": "v2.0.3" } }, [ From eba10b7471c8deb08302731834af9a283c362510 Mon Sep 17 00:00:00 2001 From: Hanh Hoang <134130358+sainsachiko@users.noreply.github.com> Date: Fri, 15 May 2026 15:58:57 +0100 Subject: [PATCH 6/7] Fix release tag Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index e2e191b3..81366e54 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [[v2.0.3](https://github.com/sanger-tol/readmapping/releases/tag/2.0.2)] - Hungarian Horntail (patch 3) - [2026-05-15] +## [[v2.0.3](https://github.com/sanger-tol/readmapping/releases/tag/2.0.3)] - Hungarian Horntail (patch 3) - [2026-05-15] ### Enhancements & fixes From 0916ea57887b376f8c99b8cc5a4b1e796bcee0b2 Mon Sep 17 00:00:00 2001 From: Hanh Hoang <134130358+sainsachiko@users.noreply.github.com> Date: Fri, 15 May 2026 16:00:05 +0100 Subject: [PATCH 7/7] Fix patch name Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- CITATION.cff | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CITATION.cff b/CITATION.cff index 49241964..bfb43879 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -57,7 +57,7 @@ license: MIT message: If you use this software, please cite it using the metadata from this file and all references from CITATIONS.md . repository-code: https://github.com/sanger-tol/readmapping -title: sanger-tol/readmapping v2.0.3 - Hungarian Horntail (patch 2) +title: sanger-tol/readmapping v2.0.3 - Hungarian Horntail (patch 3) type: software url: https://pipelines.tol.sanger.ac.uk/readmapping version: 2.0.3