From 19132fff4a12861e0c68b6aa959613329dafd271 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 22 Jan 2024 13:37:45 -0800 Subject: [PATCH 01/49] first commit: bump up kb versions --- modules/nf-core/kallistobustools/count/environment.yml | 2 +- modules/nf-core/kallistobustools/count/main.nf | 4 ++-- modules/nf-core/kallistobustools/ref/environment.yml | 2 +- modules/nf-core/kallistobustools/ref/main.nf | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/modules/nf-core/kallistobustools/count/environment.yml b/modules/nf-core/kallistobustools/count/environment.yml index 7ff8a2da..024f0afc 100644 --- a/modules/nf-core/kallistobustools/count/environment.yml +++ b/modules/nf-core/kallistobustools/count/environment.yml @@ -4,4 +4,4 @@ channels: - bioconda - defaults dependencies: - - bioconda::kb-python=0.27.2 + - bioconda::kb-python=0.28.2 diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index 036bb35d..bfd9a625 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -4,8 +4,8 @@ process KALLISTOBUSTOOLS_COUNT { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/kb-python:0.27.2--pyhdfd78af_0' : - 'biocontainers/kb-python:0.27.2--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_0' : + 'biocontainers/kb-python:0.28.2--pyhdfd78af_0' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/kallistobustools/ref/environment.yml b/modules/nf-core/kallistobustools/ref/environment.yml index acbd0e0a..6ae07a8c 100644 --- a/modules/nf-core/kallistobustools/ref/environment.yml +++ b/modules/nf-core/kallistobustools/ref/environment.yml @@ -4,5 +4,5 @@ channels: - bioconda - defaults dependencies: - - bioconda::kb-python=0.27.2 + - bioconda::kb-python=0.28.2 - conda-forge::requests>=2.23.0 diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf index 68d72ca9..759e8663 100644 --- a/modules/nf-core/kallistobustools/ref/main.nf +++ b/modules/nf-core/kallistobustools/ref/main.nf @@ -4,8 +4,8 @@ process KALLISTOBUSTOOLS_REF { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/kb-python:0.27.2--pyhdfd78af_0' : - 'biocontainers/kb-python:0.27.2--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_0' : + 'biocontainers/kb-python:0.28.2--pyhdfd78af_0' }" input: path fasta From 4ef499e6d856b76e7a6010f3c0e10abb63edf940 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 29 Jan 2024 14:47:27 -0800 Subject: [PATCH 02/49] renaming parameters --- .../nf-core/kallistobustools/count/main.nf | 4 ++-- .../nf-core/kallistobustools/count/meta.yml | 10 ++++----- .../kallistobustools/ref/environment.yml | 2 +- modules/nf-core/kallistobustools/ref/main.nf | 8 +++---- modules/nf-core/kallistobustools/ref/meta.yml | 22 +++++++++---------- 5 files changed, 23 insertions(+), 23 deletions(-) diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index bfd9a625..df81a097 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -27,7 +27,7 @@ process KALLISTOBUSTOOLS_COUNT { def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" def cdna = t1c ? "-c1 $t1c" : '' - def introns = t2c ? "-c2 $t2c" : '' + def unprocessed = t2c ? "-c2 $t2c" : '' def memory = task.memory.toGiga() - 1 """ kb \\ @@ -36,7 +36,7 @@ process KALLISTOBUSTOOLS_COUNT { -i $index \\ -g $t2g \\ $cdna \\ - $introns \\ + $unprocessed \\ -x $technology \\ $args \\ -o ${prefix}.count \\ diff --git a/modules/nf-core/kallistobustools/count/meta.yml b/modules/nf-core/kallistobustools/count/meta.yml index 7491248c..c8763343 100644 --- a/modules/nf-core/kallistobustools/count/meta.yml +++ b/modules/nf-core/kallistobustools/count/meta.yml @@ -34,16 +34,16 @@ input: pattern: "*t2g.txt" - t1c: type: file - description: kb ref's c1 spliced_t2c file + description: kb ref's c1 cdna_t2c file pattern: "*.{cdna_t2c.txt}" - t2c: type: file - description: kb ref's c2 unspliced_t2c file - pattern: "*.{introns_t2c.txt}" + description: kb ref's c2 unprocessed_t2c file + pattern: "*.{unprocessed_t2c.txt}" - workflow_mode: type: string - description: String value defining workflow to use, can be one of "standard", "lamanno", "nucleus" - pattern: "{standard,lamanno,nucleus,kite}" + description: String value defining workflow to use, can be one of "standard", "nac", "lamanno" (obsolete) + pattern: "{standard,lamanno,nac}" - technology: type: string description: String value defining the sequencing technology used. diff --git a/modules/nf-core/kallistobustools/ref/environment.yml b/modules/nf-core/kallistobustools/ref/environment.yml index 6ae07a8c..62942e01 100644 --- a/modules/nf-core/kallistobustools/ref/environment.yml +++ b/modules/nf-core/kallistobustools/ref/environment.yml @@ -5,4 +5,4 @@ channels: - defaults dependencies: - bioconda::kb-python=0.28.2 - - conda-forge::requests>=2.23.0 + - conda-forge::requests>=2.23.0 \ No newline at end of file diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf index 759e8663..989f86f3 100644 --- a/modules/nf-core/kallistobustools/ref/main.nf +++ b/modules/nf-core/kallistobustools/ref/main.nf @@ -17,9 +17,9 @@ process KALLISTOBUSTOOLS_REF { path "kb_ref_out.idx" , emit: index path "t2g.txt" , emit: t2g path "cdna.fa" , emit: cdna - path "intron.fa" , optional:true, emit: intron + path "unprocessed.fa" , optional:true, emit: unprocessed path "cdna_t2c.txt" , optional:true, emit: cdna_t2c - path "intron_t2c.txt" , optional:true, emit: intron_t2c + path "unprocessed_t2c.txt" , optional:true, emit: unprocessed_t2c when: task.ext.when == null || task.ext.when @@ -49,9 +49,9 @@ process KALLISTOBUSTOOLS_REF { -i kb_ref_out.idx \\ -g t2g.txt \\ -f1 cdna.fa \\ - -f2 intron.fa \\ + -f2 unprocessed.fa \\ -c1 cdna_t2c.txt \\ - -c2 intron_t2c.txt \\ + -c2 unprocessed_t2c.txt \\ --workflow $workflow_mode \\ $fasta \\ $gtf diff --git a/modules/nf-core/kallistobustools/ref/meta.yml b/modules/nf-core/kallistobustools/ref/meta.yml index 00be5143..1ca31c57 100644 --- a/modules/nf-core/kallistobustools/ref/meta.yml +++ b/modules/nf-core/kallistobustools/ref/meta.yml @@ -26,8 +26,8 @@ input: pattern: "*.{gtf,gtf.gz}" - workflow_mode: type: string - description: String value defining workflow to use, can be one of "standard", "lamanno", "nucleus" - pattern: "{standard,lamanno,nucleus}" + description: String value defining workflow to use, can be one of "standard", "nac", "lamanno" (obsolete) + pattern: "{standard,lamanno,nac}" output: - versions: type: file @@ -43,21 +43,21 @@ output: pattern: "*t2g.{txt}" - cdna: type: file - description: Cdna fasta file + description: cDNA fasta file pattern: "*cdna.{fa}" - - intron: + - unprocessed: type: file - description: intron fasta file - pattern: "*intron.{fa}" + description: Unprocessed fasta file + pattern: "*unprocessed.{fa}" - cdna_t2c: type: file - description: cdna transcript to capture file + description: cDNA transcript to capture file pattern: "*cdna_t2c.{txt}" - - intron_t2c: + - unprocessed_t2c: type: file - description: intron transcript to capture file - pattern: "*intron_t2c.{txt}" + description: Unprocessed transcript to capture file + pattern: "*unprocessed_t2c.{txt}" authors: - - "@flowuenne" + - "@flowuenne" maintainers: - "@flowuenne" From fb6db73e2c2a928222e79ebad7ba61f2f0f239b1 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 29 Jan 2024 14:56:45 -0800 Subject: [PATCH 03/49] Memory arg might need to be before fastq list? --- modules/nf-core/kallistobustools/count/main.nf | 4 ++-- subworkflows/local/kallisto_bustools.nf | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index df81a097..fac39a91 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -40,8 +40,8 @@ process KALLISTOBUSTOOLS_COUNT { -x $technology \\ $args \\ -o ${prefix}.count \\ - ${reads.join( " " )} \\ - -m ${memory}G + -m ${memory}G \\ + ${reads.join( " " )} cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 3210e47a..41387683 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -46,7 +46,7 @@ workflow KALLISTO_BUSTOOLS { kallisto_index = KALLISTOBUSTOOLS_REF.out.index.collect() ch_versions = ch_versions.mix(KALLISTOBUSTOOLS_REF.out.versions) t1c = KALLISTOBUSTOOLS_REF.out.cdna_t2c.ifEmpty{ [] } - t2c = KALLISTOBUSTOOLS_REF.out.intron_t2c.ifEmpty{ [] } + t2c = KALLISTOBUSTOOLS_REF.out.unprocessed_t2c.ifEmpty{ [] } } /* From 3ccd0833c6509aab95beeae252ae702ad1b7d955 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 29 Jan 2024 15:35:06 -0800 Subject: [PATCH 04/49] Update main.nf --- modules/nf-core/kallistobustools/count/main.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index fac39a91..9e860241 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -41,7 +41,7 @@ process KALLISTOBUSTOOLS_COUNT { $args \\ -o ${prefix}.count \\ -m ${memory}G \\ - ${reads.join( " " )} + ${reads.join( " " )} cat <<-END_VERSIONS > versions.yml "${task.process}": From 45e0b1963f36164f6dbf6db672825b8b7b52724a Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Fri, 9 Feb 2024 16:55:00 -0800 Subject: [PATCH 05/49] Removed t2g versions call MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit That is not really what this argument does – it just concatenates the gene_version and transcript_version fields to IDs. --- subworkflows/local/kallisto_bustools.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 41387683..8de01794 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -34,7 +34,7 @@ workflow KALLISTO_BUSTOOLS { if (!txp2gene && kallisto_index) { GENE_MAP( gtf ) txp2gene = GENE_MAP.out.gene_map - ch_versions = ch_versions.mix(GENE_MAP.out.versions) + /* -- ch_versions = ch_versions.mix(GENE_MAP.out.versions) -- */ } /* From 50d3948ba65aa88644fa18bc8ee6240fe6760ce4 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 12 Feb 2024 11:18:22 -0800 Subject: [PATCH 06/49] removing t2g.py The txp2gene file should really be generated by kallisto|bustools. The t2g.py script generates a 3-column rather than 7-column t2g, which seems to be incompatible with kb count. --- modules/local/gene_map.nf | 34 ------------------------- subworkflows/local/kallisto_bustools.nf | 20 +++------------ 2 files changed, 3 insertions(+), 51 deletions(-) delete mode 100644 modules/local/gene_map.nf diff --git a/modules/local/gene_map.nf b/modules/local/gene_map.nf deleted file mode 100644 index 9fd29e0a..00000000 --- a/modules/local/gene_map.nf +++ /dev/null @@ -1,34 +0,0 @@ -/* - * Reformat design file and check validity - */ -process GENE_MAP { - tag "$gtf" - label 'process_low' - - conda "conda-forge::python=3.8.3" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'biocontainers/python:3.8.3' }" - - input: - path gtf - - output: - path "transcripts_to_genes.txt" , emit: gene_map - - when: - task.ext.when == null || task.ext.when - - script: - if("${gtf}".endsWith('.gz')){ - name = "${gtf.baseName}" - unzip = "gunzip -f ${gtf}" - } else { - unzip = "" - name = "${gtf}" - } - """ - $unzip - cat $name | t2g.py --use_version > transcripts_to_genes.txt - """ -} diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 8de01794..7edd98d5 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -1,5 +1,4 @@ /* -- IMPORT LOCAL MODULES/SUBWORKFLOWS -- */ -include { GENE_MAP } from '../../modules/local/gene_map' include {KALLISTOBUSTOOLS_COUNT } from '../../modules/nf-core/kallistobustools/count/main' /* -- IMPORT NF-CORE MODULES/SUBWORKFLOWS -- */ @@ -21,26 +20,13 @@ workflow KALLISTO_BUSTOOLS { main: ch_versions = Channel.empty() - assert kallisto_index || (genome_fasta && gtf): + assert (txp2gene && kallisto_index) || (genome_fasta && gtf): "Must provide a genome fasta file ('--fasta') and a gtf file ('--gtf') if no index is given!" - assert txp2gene || gtf: - "Must provide either a GTF file ('--gtf') or kallisto gene map ('--kallisto_gene_map') to align with kallisto bustools!" - - /* - * Generate Kallisto Gene Map if not supplied and index is given - * If no index is given, the gene map will be generated in the 'kb ref' step - */ - if (!txp2gene && kallisto_index) { - GENE_MAP( gtf ) - txp2gene = GENE_MAP.out.gene_map - /* -- ch_versions = ch_versions.mix(GENE_MAP.out.versions) -- */ - } - /* - * Generate kallisto index + * Generate kallisto index and t2g if not already present */ - if (!kallisto_index) { + if (!(txp2gene && kallisto_index)) { KALLISTOBUSTOOLS_REF( genome_fasta, gtf, kb_workflow ) txp2gene = KALLISTOBUSTOOLS_REF.out.t2g.collect() kallisto_index = KALLISTOBUSTOOLS_REF.out.index.collect() From b0d7c5d0dcd523d0c0c143d6a00a7f4c16bcbdd3 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 12 Feb 2024 11:20:40 -0800 Subject: [PATCH 07/49] Remove txp2gene.collect() call This .collect() is incompatible with passing in an existing t2g, and superfluous given the .collect() after the kb ref call. --- subworkflows/local/kallisto_bustools.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 7edd98d5..5b3283a4 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -52,7 +52,7 @@ workflow KALLISTO_BUSTOOLS { emit: ch_versions counts = KALLISTOBUSTOOLS_COUNT.out.count - txp2gene = txp2gene.collect() + txp2gene } From 8630ef926817af9fc071143d2e476888305e9f04 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 12 Feb 2024 13:21:15 -0800 Subject: [PATCH 08/49] add t1c/t2c parameters to schema t1c and t2c are required to run nac and lamanno count workflows. Since they are already defined when running kb ref, they cannot be easily defined through ext.args when using an existing reference --- nextflow.config | 4 +++- nextflow_schema.json | 10 ++++++++++ subworkflows/local/kallisto_bustools.nf | 2 ++ 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/nextflow.config b/nextflow.config index 9e83c42a..9c3ac851 100644 --- a/nextflow.config +++ b/nextflow.config @@ -26,10 +26,12 @@ params { txp2gene = null salmon_index = null - // kallist bustools parameters + // kallisto bustools parameters kallisto_gene_map = null kallisto_index = null kb_workflow = "standard" + kb_t1c = null + kb_t2c = null // STARsolo parameters star_index = null diff --git a/nextflow_schema.json b/nextflow_schema.json index 34af4c64..e9ca04d9 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -213,6 +213,16 @@ "description": "Specify a path to the precomputed Kallisto index.", "fa_icon": "fas fa-fish" }, + "kb_t1c": { + "type": "string", + "description": "Specify a path to the cDNA transcripts-to-capture.", + "fa_icon": "fas fa-fish" + }, + "kb_t2c": { + "type": "string", + "description": "Specify a path to the intron transcripts-to-capture.", + "fa_icon": "fas fa-fish" + }, "kb_workflow": { "type": "string", "default": "standard", diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 5b3283a4..7fdaf8ef 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -13,6 +13,8 @@ workflow KALLISTO_BUSTOOLS { gtf kallisto_index txp2gene + t1c + t2c protocol kb_workflow ch_fastq From e503e218326fa852fb95ac2d77d88e20fec1d1d9 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 12 Feb 2024 13:29:55 -0800 Subject: [PATCH 09/49] Fixed kallisto_gene_map documentation scrnaseq does not actually use kallisto_gene_map anywhere. Changed kallisto icon from a salmon to a rainbow (there is no bear icon, but bustools uses the Pink Floyd-esque prism image, so it seems most appropriate) --- nextflow_schema.json | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index e9ca04d9..b94b6460 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -155,7 +155,7 @@ "txp2gene": { "type": "string", "description": "Path to transcript to gene mapping file. This allows the specification of a transcript to gene mapping file for Salmon Alevin and AlevinQC.", - "help_text": "> This is not the same as the `kallisto_gene_map` parameter down below and is only used by the Salmon Alevin workflow.", + "help_text": "> This is the same as the `kallisto_gene_map` parameter below.", "fa_icon": "fas fa-map-marked-alt" }, "simpleaf_rlen": { @@ -203,31 +203,31 @@ "default": "", "fa_icon": "fas fa-fish", "properties": { - "kallisto_gene_map": { - "type": "string", - "description": "Specify a Kallisto gene mapping file here. If you don't, this will be automatically created in the Kallisto workflow when specifying a valid `--gtf` file.", - "fa_icon": "fas fa-fish" - }, "kallisto_index": { "type": "string", "description": "Specify a path to the precomputed Kallisto index.", - "fa_icon": "fas fa-fish" + "fa_icon": "fas fa-rainbow" + }, + "txp2gene": { + "type": "string", + "description": "Specify a Kallisto gene mapping file here. If you don't, this will be automatically created in the Kallisto workflow when specifying a valid `--gtf` file.", + "fa_icon": "fas fa-rainbow" }, "kb_t1c": { "type": "string", "description": "Specify a path to the cDNA transcripts-to-capture.", - "fa_icon": "fas fa-fish" + "fa_icon": "fas fa-rainbow" }, "kb_t2c": { "type": "string", "description": "Specify a path to the intron transcripts-to-capture.", - "fa_icon": "fas fa-fish" + "fa_icon": "fas fa-rainbow" }, "kb_workflow": { "type": "string", "default": "standard", "description": "Type of workflow. Use `lamanno` for RNA velocity based on La Manno et al. 2018 logic. Use `nucleus` for RNA velocity on single-nucleus RNA-seq reads. Use `kite` for feature barcoding. Use `kite: 10xFB` for 10x Genomics Feature Barcoding technology. (default: standard)", - "fa_icon": "fas fa-fish", + "fa_icon": "fas fa-rainbow", "enum": ["standard", "lamanno", "nucleus", "kite", "kite: 10xFB"] } } From 752d051df605dbe192339e9446162882b4657d69 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Mon, 12 Feb 2024 13:31:59 -0800 Subject: [PATCH 10/49] Update nextflow_schema.json --- nextflow_schema.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index b94b6460..56785f0e 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -201,7 +201,7 @@ "type": "object", "description": "Params related to Kallisto/BUS tool", "default": "", - "fa_icon": "fas fa-fish", + "fa_icon": "fas fa-rainbow", "properties": { "kallisto_index": { "type": "string", From 4d90d609f1ececc9421619c572b8aa8a717ab37f Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 13 Feb 2024 10:03:11 -0800 Subject: [PATCH 11/49] de-duplicating txp2gene args (lint complains) --- nextflow_schema.json | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 56785f0e..0dc716b1 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -138,7 +138,12 @@ "default": "s3://ngi-igenomes/igenomes", "fa_icon": "fas fa-cloud-download-alt", "hidden": true - } + }, + "txp2gene": { + "type": "string", + "description": "Kallisto or Alevin gene mapping file.", + "fa_icon": "fas map-marked-alt" + }, } }, "alevin_options": { @@ -152,12 +157,6 @@ "description": "This can be used to specify a precomputed Salmon index in the pipeline, in order to skip the generation of required indices by Salmon itself.", "fa_icon": "fas fa-fish" }, - "txp2gene": { - "type": "string", - "description": "Path to transcript to gene mapping file. This allows the specification of a transcript to gene mapping file for Salmon Alevin and AlevinQC.", - "help_text": "> This is the same as the `kallisto_gene_map` parameter below.", - "fa_icon": "fas fa-map-marked-alt" - }, "simpleaf_rlen": { "type": "integer", "default": 91, @@ -208,11 +207,6 @@ "description": "Specify a path to the precomputed Kallisto index.", "fa_icon": "fas fa-rainbow" }, - "txp2gene": { - "type": "string", - "description": "Specify a Kallisto gene mapping file here. If you don't, this will be automatically created in the Kallisto workflow when specifying a valid `--gtf` file.", - "fa_icon": "fas fa-rainbow" - }, "kb_t1c": { "type": "string", "description": "Specify a path to the cDNA transcripts-to-capture.", From efb1487d0a6bf6037c789121eeacf63173ba680c Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 13 Feb 2024 10:05:39 -0800 Subject: [PATCH 12/49] Update nextflow_schema.json --- nextflow_schema.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 0dc716b1..837ba7a0 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -143,7 +143,7 @@ "type": "string", "description": "Kallisto or Alevin gene mapping file.", "fa_icon": "fas map-marked-alt" - }, + } } }, "alevin_options": { From 5ffdc888b8f31e53e7aae1f4d633bb70634a6785 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 13 Feb 2024 10:22:45 -0800 Subject: [PATCH 13/49] txp2gene has to be moved if it's shared --- nextflow.config | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/nextflow.config b/nextflow.config index 9c3ac851..a774d835 100644 --- a/nextflow.config +++ b/nextflow.config @@ -19,15 +19,14 @@ params { // reference files genome = null transcript_fasta = null + txp2gene = null // salmon alevin parameters (simpleaf) simpleaf_rlen = 91 barcode_whitelist = null - txp2gene = null salmon_index = null // kallisto bustools parameters - kallisto_gene_map = null kallisto_index = null kb_workflow = "standard" kb_t1c = null From 38344a5018c0eaffdd6d7552dcb44b98d5133227 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 13 Feb 2024 10:44:28 -0800 Subject: [PATCH 14/49] adding explicit t1c and t2c arguments for kb Maybe it is possible to somehow inject them with ext.args, but this is a fairly standard pipeline option, and should probably be exposed. --- workflows/scrnaseq.nf | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 25740a8e..63381a6f 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -98,6 +98,8 @@ if (params.barcode_whitelist) { //kallisto params ch_kallisto_index = params.kallisto_index ? file(params.kallisto_index) : [] kb_workflow = params.kb_workflow +kb_t1c = params.kb_t1c ? file(params.kb_t1c) : [] +kb_t2c = params.kb_t2c ? file(params.kb_t2c) : [] //salmon params ch_salmon_index = params.salmon_index ? file(params.salmon_index) : [] @@ -144,6 +146,8 @@ workflow SCRNASEQ { ch_filter_gtf, ch_kallisto_index, ch_txp2gene, + kb_t1c, + kb_t2c, protocol_config['protocol'], kb_workflow, ch_fastq From bee4f67a2609fdf952c86b1af3ca95f6b7fc03f7 Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Tue, 20 Feb 2024 15:30:41 +0000 Subject: [PATCH 15/49] Template update for nf-core/tools version 2.13 --- .editorconfig | 9 +- .github/workflows/awsfulltest.yml | 4 +- .github/workflows/awstest.yml | 4 +- .github/workflows/branch.yml | 2 +- .github/workflows/ci.yml | 7 +- .github/workflows/clean-up.yml | 2 +- .github/workflows/download_pipeline.yml | 17 +- .github/workflows/linting.yml | 12 +- .github/workflows/linting_comment.yml | 4 +- .github/workflows/release-announcements.yml | 11 +- README.md | 5 +- assets/multiqc_config.yml | 2 + assets/schema_input.json | 21 +- bin/check_samplesheet.py | 259 ----------- conf/modules.config | 8 - lib/NfcoreTemplate.groovy | 356 -------------- lib/Utils.groovy | 47 -- lib/WorkflowMain.groovy | 77 --- lib/WorkflowScrnaseq.groovy | 122 ----- main.nf | 100 ++-- modules.json | 28 +- modules/local/samplesheet_check.nf | 31 -- .../dumpsoftwareversions/environment.yml | 7 - .../custom/dumpsoftwareversions/main.nf | 24 - .../custom/dumpsoftwareversions/meta.yml | 37 -- .../templates/dumpsoftwareversions.py | 102 ---- .../dumpsoftwareversions/tests/main.nf.test | 43 -- .../tests/main.nf.test.snap | 33 -- .../dumpsoftwareversions/tests/tags.yml | 2 - modules/nf-core/fastqc/tests/main.nf.test | 14 +- .../nf-core/fastqc/tests/main.nf.test.snap | 76 ++- modules/nf-core/multiqc/environment.yml | 2 +- modules/nf-core/multiqc/main.nf | 4 +- modules/nf-core/multiqc/tests/main.nf.test | 13 +- .../nf-core/multiqc/tests/main.nf.test.snap | 32 +- nextflow.config | 5 +- nextflow_schema.json | 1 + pyproject.toml | 8 +- subworkflows/local/input_check.nf | 44 -- .../utils_nfcore_scrnaseq_pipeline/main.nf | 247 ++++++++++ .../nf-core/utils_nextflow_pipeline/main.nf | 126 +++++ .../nf-core/utils_nextflow_pipeline/meta.yml | 38 ++ .../tests/main.function.nf.test | 54 +++ .../tests/main.function.nf.test.snap | 12 + .../tests/main.workflow.nf.test | 123 +++++ .../tests/nextflow.config | 9 + .../utils_nextflow_pipeline/tests/tags.yml | 2 + .../nf-core/utils_nfcore_pipeline/main.nf | 440 ++++++++++++++++++ .../nf-core/utils_nfcore_pipeline/meta.yml | 24 + .../tests/main.function.nf.test | 134 ++++++ .../tests/main.function.nf.test.snap | 138 ++++++ .../tests/main.workflow.nf.test | 29 ++ .../tests/main.workflow.nf.test.snap | 15 + .../tests/nextflow.config | 9 + .../utils_nfcore_pipeline/tests/tags.yml | 2 + .../nf-core/utils_nfvalidation_plugin/main.nf | 62 +++ .../utils_nfvalidation_plugin/meta.yml | 44 ++ .../tests/main.nf.test | 200 ++++++++ .../tests/nextflow_schema.json | 96 ++++ .../utils_nfvalidation_plugin/tests/tags.yml | 2 + workflows/scrnaseq.nf | 133 ++---- 61 files changed, 2108 insertions(+), 1406 deletions(-) delete mode 100755 bin/check_samplesheet.py delete mode 100755 lib/NfcoreTemplate.groovy delete mode 100644 lib/Utils.groovy delete mode 100755 lib/WorkflowMain.groovy delete mode 100755 lib/WorkflowScrnaseq.groovy delete mode 100644 modules/local/samplesheet_check.nf delete mode 100644 modules/nf-core/custom/dumpsoftwareversions/environment.yml delete mode 100644 modules/nf-core/custom/dumpsoftwareversions/main.nf delete mode 100644 modules/nf-core/custom/dumpsoftwareversions/meta.yml delete mode 100755 modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py delete mode 100644 modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test delete mode 100644 modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap delete mode 100644 modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml delete mode 100644 subworkflows/local/input_check.nf create mode 100644 subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/main.nf create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/meta.yml create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config create mode 100644 subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/main.nf create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/meta.yml create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config create mode 100644 subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml create mode 100644 subworkflows/nf-core/utils_nfvalidation_plugin/main.nf create mode 100644 subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml create mode 100644 subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test create mode 100644 subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json create mode 100644 subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml diff --git a/.editorconfig b/.editorconfig index 9b990088..dd9ffa53 100644 --- a/.editorconfig +++ b/.editorconfig @@ -18,7 +18,12 @@ end_of_line = unset insert_final_newline = unset trim_trailing_whitespace = unset indent_style = unset -indent_size = unset +[/subworkflows/nf-core/**] +charset = unset +end_of_line = unset +insert_final_newline = unset +trim_trailing_whitespace = unset +indent_style = unset [/assets/email*] indent_size = unset @@ -28,5 +33,5 @@ indent_size = unset indent_style = unset # ignore python -[*.{py}] +[*.{py,md}] indent_style = unset diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index 33ee6733..fd263945 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,7 +14,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: seqeralabs/action-tower-launch@v2 + uses: seqeralabs/action-tower-launch@922e5c8d5ac4e918107ec311d2ebbd65e5982b3d # v2 # TODO nf-core: You can customise AWS full pipeline tests as required # Add full size test data (but still relatively small datasets for few samples) # on the `test_full.config` test runs with only one set of parameters @@ -31,7 +31,7 @@ jobs: } profiles: test_full - - uses: actions/upload-artifact@v4 + - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: Tower debug log file path: | diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index edc7b3a3..1f58192f 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -12,7 +12,7 @@ jobs: steps: # Launch workflow using Tower CLI tool action - name: Launch workflow via tower - uses: seqeralabs/action-tower-launch@v2 + uses: seqeralabs/action-tower-launch@922e5c8d5ac4e918107ec311d2ebbd65e5982b3d # v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -25,7 +25,7 @@ jobs: } profiles: test - - uses: actions/upload-artifact@v4 + - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: Tower debug log file path: | diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml index 68083c82..b7f206b8 100644 --- a/.github/workflows/branch.yml +++ b/.github/workflows/branch.yml @@ -19,7 +19,7 @@ jobs: # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets - name: Post PR comment if: failure() - uses: mshick/add-pr-comment@v2 + uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc # v2 with: message: | ## This PR is against the `master` branch :x: diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index de0c4594..e2c989ca 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -28,13 +28,16 @@ jobs: - "latest-everything" steps: - name: Check out pipeline code - uses: actions/checkout@v4 + uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 with: version: "${{ matrix.NXF_VER }}" + - name: Disk space cleanup + uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 + - name: Run pipeline with test data # TODO nf-core: You can customise CI pipeline run tests as required # For example: adding multiple test runs with different parameters diff --git a/.github/workflows/clean-up.yml b/.github/workflows/clean-up.yml index e37cfda5..0b6b1f27 100644 --- a/.github/workflows/clean-up.yml +++ b/.github/workflows/clean-up.yml @@ -10,7 +10,7 @@ jobs: issues: write pull-requests: write steps: - - uses: actions/stale@v9 + - uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9 with: stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days." stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful." diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml index 8611458a..f823210d 100644 --- a/.github/workflows/download_pipeline.yml +++ b/.github/workflows/download_pipeline.yml @@ -6,6 +6,11 @@ name: Test successful pipeline download with 'nf-core download' # - the head branch of the pull request is updated, i.e. if fixes for a release are pushed last minute to dev. on: workflow_dispatch: + inputs: + testbranch: + description: "The specific branch you wish to utilize for the test execution of nf-core download." + required: true + default: "dev" pull_request: types: - opened @@ -23,13 +28,13 @@ jobs: runs-on: ubuntu-latest steps: - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 - - uses: actions/setup-python@v5 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: "3.11" architecture: "x64" - - uses: eWaterCycle/setup-singularity@v7 + - uses: eWaterCycle/setup-singularity@931d4e31109e875b13309ae1d07c70ca8fbc8537 # v7 with: singularity-version: 3.8.3 @@ -42,13 +47,13 @@ jobs: run: | echo "REPO_LOWERCASE=${GITHUB_REPOSITORY,,}" >> ${GITHUB_ENV} echo "REPOTITLE_LOWERCASE=$(basename ${GITHUB_REPOSITORY,,})" >> ${GITHUB_ENV} - echo "REPO_BRANCH=${GITHUB_REF#refs/heads/}" >> ${GITHUB_ENV} + echo "REPO_BRANCH=${{ github.event.inputs.testbranch || 'dev' }}" >> ${GITHUB_ENV} - name: Download the pipeline env: NXF_SINGULARITY_CACHEDIR: ./ run: | - nf-core download ${{ env.REPO_LOWERCASE }} \ + nf-core download ${{ env.REPO_LOWERCASE }} \ --revision ${{ env.REPO_BRANCH }} \ --outdir ./${{ env.REPOTITLE_LOWERCASE }} \ --compress "none" \ @@ -64,4 +69,4 @@ jobs: env: NXF_SINGULARITY_CACHEDIR: ./ NXF_SINGULARITY_HOME_MOUNT: true - run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results + run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 81cd098e..748b4311 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -14,10 +14,10 @@ jobs: pre-commit: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Set up Python 3.11 - uses: actions/setup-python@v5 + uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: 3.11 cache: "pip" @@ -32,12 +32,12 @@ jobs: runs-on: ubuntu-latest steps: - name: Check out pipeline code - uses: actions/checkout@v4 + uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@v1 + uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 - - uses: actions/setup-python@v5 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: "3.11" architecture: "x64" @@ -60,7 +60,7 @@ jobs: - name: Upload linting log file artifact if: ${{ always() }} - uses: actions/upload-artifact@v4 + uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 with: name: linting-logs path: | diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml index 147bcd10..b706875f 100644 --- a/.github/workflows/linting_comment.yml +++ b/.github/workflows/linting_comment.yml @@ -11,7 +11,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Download lint results - uses: dawidd6/action-download-artifact@v3 + uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3 with: workflow: linting.yml workflow_conclusion: completed @@ -21,7 +21,7 @@ jobs: run: echo "pr_number=$(cat linting-logs/PR_number.txt)" >> $GITHUB_OUTPUT - name: Post PR comment - uses: marocchino/sticky-pull-request-comment@v2 + uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 # v2 with: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} number: ${{ steps.pr_number.outputs.pr_number }} diff --git a/.github/workflows/release-announcements.yml b/.github/workflows/release-announcements.yml index 21ac3f06..c3674af2 100644 --- a/.github/workflows/release-announcements.yml +++ b/.github/workflows/release-announcements.yml @@ -9,6 +9,11 @@ jobs: toot: runs-on: ubuntu-latest steps: + - name: get topics and convert to hashtags + id: get_topics + run: | + curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' > $GITHUB_OUTPUT + - uses: rzr/fediverse-action@master with: access-token: ${{ secrets.MASTODON_ACCESS_TOKEN }} @@ -20,11 +25,13 @@ jobs: Please see the changelog: ${{ github.event.release.html_url }} + ${{ steps.get_topics.outputs.GITHUB_OUTPUT }} #nfcore #openscience #nextflow #bioinformatics + send-tweet: runs-on: ubuntu-latest steps: - - uses: actions/setup-python@v5 + - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: python-version: "3.10" - name: Install dependencies @@ -56,7 +63,7 @@ jobs: bsky-post: runs-on: ubuntu-latest steps: - - uses: zentered/bluesky-post-action@v0.1.0 + - uses: zentered/bluesky-post-action@80dbe0a7697de18c15ad22f4619919ceb5ccf597 # v0.1.0 with: post: | Pipeline release! ${{ github.repository }} v${{ github.event.release.tag_name }} - ${{ github.event.release.name }}! diff --git a/README.md b/README.md index f997b3d7..c80f96b1 100644 --- a/README.md +++ b/README.md @@ -4,8 +4,9 @@ nf-core/scrnaseq -[![GitHub Actions CI Status](https://github.com/nf-core/scrnaseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/scrnaseq/actions?query=workflow%3A%22nf-core+CI%22) -[![GitHub Actions Linting Status](https://github.com/nf-core/scrnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/scrnaseq/actions?query=workflow%3A%22nf-core+linting%22)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/scrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) + +[![GitHub Actions CI Status](https://github.com/nf-core/scrnaseq/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/scrnaseq/actions/workflows/ci.yml) +[![GitHub Actions Linting Status](https://github.com/nf-core/scrnaseq/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/scrnaseq/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/scrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/) [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/) diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 051ed54e..584bae69 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -11,3 +11,5 @@ report_section_order: order: -1002 export_plots: true + +disable_version_detection: true diff --git a/assets/schema_input.json b/assets/schema_input.json index 0a93254d..dab0450a 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -10,25 +10,22 @@ "sample": { "type": "string", "pattern": "^\\S+$", - "errorMessage": "Sample name must be provided and cannot contain spaces" + "errorMessage": "Sample name must be provided and cannot contain spaces", + "meta": ["id"] }, "fastq_1": { "type": "string", + "format": "file-path", + "exists": true, "pattern": "^\\S+\\.f(ast)?q\\.gz$", "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'" }, "fastq_2": { - "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'", - "anyOf": [ - { - "type": "string", - "pattern": "^\\S+\\.f(ast)?q\\.gz$" - }, - { - "type": "string", - "maxLength": 0 - } - ] + "type": "string", + "format": "file-path", + "exists": true, + "pattern": "^\\S+\\.f(ast)?q\\.gz$", + "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'" } }, "required": ["sample", "fastq_1"] diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py deleted file mode 100755 index 4a758fe0..00000000 --- a/bin/check_samplesheet.py +++ /dev/null @@ -1,259 +0,0 @@ -#!/usr/bin/env python - - -"""Provide a command line tool to validate and transform tabular samplesheets.""" - - -import argparse -import csv -import logging -import sys -from collections import Counter -from pathlib import Path - -logger = logging.getLogger() - - -class RowChecker: - """ - Define a service that can validate and transform each given row. - - Attributes: - modified (list): A list of dicts, where each dict corresponds to a previously - validated and transformed row. The order of rows is maintained. - - """ - - VALID_FORMATS = ( - ".fq.gz", - ".fastq.gz", - ) - - def __init__( - self, - sample_col="sample", - first_col="fastq_1", - second_col="fastq_2", - single_col="single_end", - **kwargs, - ): - """ - Initialize the row checker with the expected column names. - - Args: - sample_col (str): The name of the column that contains the sample name - (default "sample"). - first_col (str): The name of the column that contains the first (or only) - FASTQ file path (default "fastq_1"). - second_col (str): The name of the column that contains the second (if any) - FASTQ file path (default "fastq_2"). - single_col (str): The name of the new column that will be inserted and - records whether the sample contains single- or paired-end sequencing - reads (default "single_end"). - - """ - super().__init__(**kwargs) - self._sample_col = sample_col - self._first_col = first_col - self._second_col = second_col - self._single_col = single_col - self._seen = set() - self.modified = [] - - def validate_and_transform(self, row): - """ - Perform all validations on the given row and insert the read pairing status. - - Args: - row (dict): A mapping from column headers (keys) to elements of that row - (values). - - """ - self._validate_sample(row) - self._validate_first(row) - self._validate_second(row) - self._validate_pair(row) - self._seen.add((row[self._sample_col], row[self._first_col])) - self.modified.append(row) - - def _validate_sample(self, row): - """Assert that the sample name exists and convert spaces to underscores.""" - if len(row[self._sample_col]) <= 0: - raise AssertionError("Sample input is required.") - # Sanitize samples slightly. - row[self._sample_col] = row[self._sample_col].replace(" ", "_") - - def _validate_first(self, row): - """Assert that the first FASTQ entry is non-empty and has the right format.""" - if len(row[self._first_col]) <= 0: - raise AssertionError("At least the first FASTQ file is required.") - self._validate_fastq_format(row[self._first_col]) - - def _validate_second(self, row): - """Assert that the second FASTQ entry has the right format if it exists.""" - if len(row[self._second_col]) > 0: - self._validate_fastq_format(row[self._second_col]) - - def _validate_pair(self, row): - """Assert that read pairs have the same file extension. Report pair status.""" - if row[self._first_col] and row[self._second_col]: - row[self._single_col] = False - first_col_suffix = Path(row[self._first_col]).suffixes[-2:] - second_col_suffix = Path(row[self._second_col]).suffixes[-2:] - if first_col_suffix != second_col_suffix: - raise AssertionError("FASTQ pairs must have the same file extensions.") - else: - row[self._single_col] = True - - def _validate_fastq_format(self, filename): - """Assert that a given filename has one of the expected FASTQ extensions.""" - if not any(filename.endswith(extension) for extension in self.VALID_FORMATS): - raise AssertionError( - f"The FASTQ file has an unrecognized extension: {filename}\n" - f"It should be one of: {', '.join(self.VALID_FORMATS)}" - ) - - def validate_unique_samples(self): - """ - Assert that the combination of sample name and FASTQ filename is unique. - - In addition to the validation, also rename all samples to have a suffix of _T{n}, where n is the - number of times the same sample exist, but with different FASTQ files, e.g., multiple runs per experiment. - - """ - if len(self._seen) != len(self.modified): - raise AssertionError("The pair of sample name and FASTQ must be unique.") - seen = Counter() - for row in self.modified: - sample = row[self._sample_col] - seen[sample] += 1 - row[self._sample_col] = f"{sample}_T{seen[sample]}" - - -def read_head(handle, num_lines=10): - """Read the specified number of lines from the current position in the file.""" - lines = [] - for idx, line in enumerate(handle): - if idx == num_lines: - break - lines.append(line) - return "".join(lines) - - -def sniff_format(handle): - """ - Detect the tabular format. - - Args: - handle (text file): A handle to a `text file`_ object. The read position is - expected to be at the beginning (index 0). - - Returns: - csv.Dialect: The detected tabular format. - - .. _text file: - https://docs.python.org/3/glossary.html#term-text-file - - """ - peek = read_head(handle) - handle.seek(0) - sniffer = csv.Sniffer() - dialect = sniffer.sniff(peek) - return dialect - - -def check_samplesheet(file_in, file_out): - """ - Check that the tabular samplesheet has the structure expected by nf-core pipelines. - - Validate the general shape of the table, expected columns, and each row. Also add - an additional column which records whether one or two FASTQ reads were found. - - Args: - file_in (pathlib.Path): The given tabular samplesheet. The format can be either - CSV, TSV, or any other format automatically recognized by ``csv.Sniffer``. - file_out (pathlib.Path): Where the validated and transformed samplesheet should - be created; always in CSV format. - - Example: - This function checks that the samplesheet follows the following structure, - see also the `viral recon samplesheet`_:: - - sample,fastq_1,fastq_2 - SAMPLE_PE,SAMPLE_PE_RUN1_1.fastq.gz,SAMPLE_PE_RUN1_2.fastq.gz - SAMPLE_PE,SAMPLE_PE_RUN2_1.fastq.gz,SAMPLE_PE_RUN2_2.fastq.gz - SAMPLE_SE,SAMPLE_SE_RUN1_1.fastq.gz, - - .. _viral recon samplesheet: - https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv - - """ - required_columns = {"sample", "fastq_1", "fastq_2"} - # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`. - with file_in.open(newline="") as in_handle: - reader = csv.DictReader(in_handle, dialect=sniff_format(in_handle)) - # Validate the existence of the expected header columns. - if not required_columns.issubset(reader.fieldnames): - req_cols = ", ".join(required_columns) - logger.critical(f"The sample sheet **must** contain these column headers: {req_cols}.") - sys.exit(1) - # Validate each row. - checker = RowChecker() - for i, row in enumerate(reader): - try: - checker.validate_and_transform(row) - except AssertionError as error: - logger.critical(f"{str(error)} On line {i + 2}.") - sys.exit(1) - checker.validate_unique_samples() - header = list(reader.fieldnames) - header.insert(1, "single_end") - # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`. - with file_out.open(mode="w", newline="") as out_handle: - writer = csv.DictWriter(out_handle, header, delimiter=",") - writer.writeheader() - for row in checker.modified: - writer.writerow(row) - - -def parse_args(argv=None): - """Define and immediately parse command line arguments.""" - parser = argparse.ArgumentParser( - description="Validate and transform a tabular samplesheet.", - epilog="Example: python check_samplesheet.py samplesheet.csv samplesheet.valid.csv", - ) - parser.add_argument( - "file_in", - metavar="FILE_IN", - type=Path, - help="Tabular input samplesheet in CSV or TSV format.", - ) - parser.add_argument( - "file_out", - metavar="FILE_OUT", - type=Path, - help="Transformed output samplesheet in CSV format.", - ) - parser.add_argument( - "-l", - "--log-level", - help="The desired log level (default WARNING).", - choices=("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"), - default="WARNING", - ) - return parser.parse_args(argv) - - -def main(argv=None): - """Coordinate argument parsing and program execution.""" - args = parse_args(argv) - logging.basicConfig(level=args.log_level, format="[%(levelname)s] %(message)s") - if not args.file_in.is_file(): - logger.error(f"The given input file {args.file_in} was not found!") - sys.exit(2) - args.file_out.parent.mkdir(parents=True, exist_ok=True) - check_samplesheet(args.file_in, args.file_out) - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/conf/modules.config b/conf/modules.config index d91c6aba..e3ea8fa6 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -18,14 +18,6 @@ process { saveAs: { filename -> filename.equals('versions.yml') ? null : filename } ] - withName: SAMPLESHEET_CHECK { - publishDir = [ - path: { "${params.outdir}/pipeline_info" }, - mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } - ] - } - withName: FASTQC { ext.args = '--quiet' } diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy deleted file mode 100755 index e248e4c3..00000000 --- a/lib/NfcoreTemplate.groovy +++ /dev/null @@ -1,356 +0,0 @@ -// -// This file holds several functions used within the nf-core pipeline template. -// - -import org.yaml.snakeyaml.Yaml -import groovy.json.JsonOutput -import nextflow.extension.FilesEx - -class NfcoreTemplate { - - // - // Check AWS Batch related parameters have been specified correctly - // - public static void awsBatch(workflow, params) { - if (workflow.profile.contains('awsbatch')) { - // Check params.awsqueue and params.awsregion have been set if running on AWSBatch - assert (params.awsqueue && params.awsregion) : "Specify correct --awsqueue and --awsregion parameters on AWSBatch!" - // Check outdir paths to be S3 buckets if running on AWSBatch - assert params.outdir.startsWith('s3:') : "Outdir not on S3 - specify S3 Bucket to run on AWSBatch!" - } - } - - // - // Warn if a -profile or Nextflow config has not been provided to run the pipeline - // - public static void checkConfigProvided(workflow, log) { - if (workflow.profile == 'standard' && workflow.configFiles.size() <= 1) { - log.warn "[$workflow.manifest.name] You are attempting to run the pipeline without any custom configuration!\n\n" + - "This will be dependent on your local compute environment but can be achieved via one or more of the following:\n" + - " (1) Using an existing pipeline profile e.g. `-profile docker` or `-profile singularity`\n" + - " (2) Using an existing nf-core/configs for your Institution e.g. `-profile crick` or `-profile uppmax`\n" + - " (3) Using your own local custom config e.g. `-c /path/to/your/custom.config`\n\n" + - "Please refer to the quick start section and usage docs for the pipeline.\n " - } - } - - // - // Generate version string - // - public static String version(workflow) { - String version_string = "" - - if (workflow.manifest.version) { - def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : '' - version_string += "${prefix_v}${workflow.manifest.version}" - } - - if (workflow.commitId) { - def git_shortsha = workflow.commitId.substring(0, 7) - version_string += "-g${git_shortsha}" - } - - return version_string - } - - // - // Construct and send completion email - // - public static void email(workflow, params, summary_params, projectDir, log, multiqc_report=[]) { - - // Set up the e-mail variables - def subject = "[$workflow.manifest.name] Successful: $workflow.runName" - if (!workflow.success) { - subject = "[$workflow.manifest.name] FAILED: $workflow.runName" - } - - def summary = [:] - for (group in summary_params.keySet()) { - summary << summary_params[group] - } - - def misc_fields = [:] - misc_fields['Date Started'] = workflow.start - misc_fields['Date Completed'] = workflow.complete - misc_fields['Pipeline script file path'] = workflow.scriptFile - misc_fields['Pipeline script hash ID'] = workflow.scriptId - if (workflow.repository) misc_fields['Pipeline repository Git URL'] = workflow.repository - if (workflow.commitId) misc_fields['Pipeline repository Git Commit'] = workflow.commitId - if (workflow.revision) misc_fields['Pipeline Git branch/tag'] = workflow.revision - misc_fields['Nextflow Version'] = workflow.nextflow.version - misc_fields['Nextflow Build'] = workflow.nextflow.build - misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp - - def email_fields = [:] - email_fields['version'] = NfcoreTemplate.version(workflow) - email_fields['runName'] = workflow.runName - email_fields['success'] = workflow.success - email_fields['dateComplete'] = workflow.complete - email_fields['duration'] = workflow.duration - email_fields['exitStatus'] = workflow.exitStatus - email_fields['errorMessage'] = (workflow.errorMessage ?: 'None') - email_fields['errorReport'] = (workflow.errorReport ?: 'None') - email_fields['commandLine'] = workflow.commandLine - email_fields['projectDir'] = workflow.projectDir - email_fields['summary'] = summary << misc_fields - - // On success try attach the multiqc report - def mqc_report = null - try { - if (workflow.success) { - mqc_report = multiqc_report.getVal() - if (mqc_report.getClass() == ArrayList && mqc_report.size() >= 1) { - if (mqc_report.size() > 1) { - log.warn "[$workflow.manifest.name] Found multiple reports from process 'MULTIQC', will use only one" - } - mqc_report = mqc_report[0] - } - } - } catch (all) { - if (multiqc_report) { - log.warn "[$workflow.manifest.name] Could not attach MultiQC report to summary email" - } - } - - // Check if we are only sending emails on failure - def email_address = params.email - if (!params.email && params.email_on_fail && !workflow.success) { - email_address = params.email_on_fail - } - - // Render the TXT template - def engine = new groovy.text.GStringTemplateEngine() - def tf = new File("$projectDir/assets/email_template.txt") - def txt_template = engine.createTemplate(tf).make(email_fields) - def email_txt = txt_template.toString() - - // Render the HTML template - def hf = new File("$projectDir/assets/email_template.html") - def html_template = engine.createTemplate(hf).make(email_fields) - def email_html = html_template.toString() - - // Render the sendmail template - def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit - def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] - def sf = new File("$projectDir/assets/sendmail_template.txt") - def sendmail_template = engine.createTemplate(sf).make(smail_fields) - def sendmail_html = sendmail_template.toString() - - // Send the HTML e-mail - Map colors = logColours(params.monochrome_logs) - if (email_address) { - try { - if (params.plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } - // Try to send HTML e-mail using sendmail - def sendmail_tf = new File(workflow.launchDir.toString(), ".sendmail_tmp.html") - sendmail_tf.withWriter { w -> w << sendmail_html } - [ 'sendmail', '-t' ].execute() << sendmail_html - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-" - } catch (all) { - // Catch failures and try with plaintext - def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] - if ( mqc_report != null && mqc_report.size() <= max_multiqc_email_size.toBytes() ) { - mail_cmd += [ '-A', mqc_report ] - } - mail_cmd.execute() << email_html - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-" - } - } - - // Write summary e-mail HTML to a file - def output_hf = new File(workflow.launchDir.toString(), ".pipeline_report.html") - output_hf.withWriter { w -> w << email_html } - FilesEx.copyTo(output_hf.toPath(), "${params.outdir}/pipeline_info/pipeline_report.html"); - output_hf.delete() - - // Write summary e-mail TXT to a file - def output_tf = new File(workflow.launchDir.toString(), ".pipeline_report.txt") - output_tf.withWriter { w -> w << email_txt } - FilesEx.copyTo(output_tf.toPath(), "${params.outdir}/pipeline_info/pipeline_report.txt"); - output_tf.delete() - } - - // - // Construct and send a notification to a web server as JSON - // e.g. Microsoft Teams and Slack - // - public static void IM_notification(workflow, params, summary_params, projectDir, log) { - def hook_url = params.hook_url - - def summary = [:] - for (group in summary_params.keySet()) { - summary << summary_params[group] - } - - def misc_fields = [:] - misc_fields['start'] = workflow.start - misc_fields['complete'] = workflow.complete - misc_fields['scriptfile'] = workflow.scriptFile - misc_fields['scriptid'] = workflow.scriptId - if (workflow.repository) misc_fields['repository'] = workflow.repository - if (workflow.commitId) misc_fields['commitid'] = workflow.commitId - if (workflow.revision) misc_fields['revision'] = workflow.revision - misc_fields['nxf_version'] = workflow.nextflow.version - misc_fields['nxf_build'] = workflow.nextflow.build - misc_fields['nxf_timestamp'] = workflow.nextflow.timestamp - - def msg_fields = [:] - msg_fields['version'] = NfcoreTemplate.version(workflow) - msg_fields['runName'] = workflow.runName - msg_fields['success'] = workflow.success - msg_fields['dateComplete'] = workflow.complete - msg_fields['duration'] = workflow.duration - msg_fields['exitStatus'] = workflow.exitStatus - msg_fields['errorMessage'] = (workflow.errorMessage ?: 'None') - msg_fields['errorReport'] = (workflow.errorReport ?: 'None') - msg_fields['commandLine'] = workflow.commandLine.replaceFirst(/ +--hook_url +[^ ]+/, "") - msg_fields['projectDir'] = workflow.projectDir - msg_fields['summary'] = summary << misc_fields - - // Render the JSON template - def engine = new groovy.text.GStringTemplateEngine() - // Different JSON depending on the service provider - // Defaults to "Adaptive Cards" (https://adaptivecards.io), except Slack which has its own format - def json_path = hook_url.contains("hooks.slack.com") ? "slackreport.json" : "adaptivecard.json" - def hf = new File("$projectDir/assets/${json_path}") - def json_template = engine.createTemplate(hf).make(msg_fields) - def json_message = json_template.toString() - - // POST - def post = new URL(hook_url).openConnection(); - post.setRequestMethod("POST") - post.setDoOutput(true) - post.setRequestProperty("Content-Type", "application/json") - post.getOutputStream().write(json_message.getBytes("UTF-8")); - def postRC = post.getResponseCode(); - if (! postRC.equals(200)) { - log.warn(post.getErrorStream().getText()); - } - } - - // - // Dump pipeline parameters in a json file - // - public static void dump_parameters(workflow, params) { - def timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') - def filename = "params_${timestamp}.json" - def temp_pf = new File(workflow.launchDir.toString(), ".${filename}") - def jsonStr = JsonOutput.toJson(params) - temp_pf.text = JsonOutput.prettyPrint(jsonStr) - - FilesEx.copyTo(temp_pf.toPath(), "${params.outdir}/pipeline_info/params_${timestamp}.json") - temp_pf.delete() - } - - // - // Print pipeline summary on completion - // - public static void summary(workflow, params, log) { - Map colors = logColours(params.monochrome_logs) - if (workflow.success) { - if (workflow.stats.ignoredCount == 0) { - log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Pipeline completed successfully${colors.reset}-" - } else { - log.info "-${colors.purple}[$workflow.manifest.name]${colors.yellow} Pipeline completed successfully, but with errored process(es) ${colors.reset}-" - } - } else { - log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed with errors${colors.reset}-" - } - } - - // - // ANSII Colours used for terminal logging - // - public static Map logColours(Boolean monochrome_logs) { - Map colorcodes = [:] - - // Reset / Meta - colorcodes['reset'] = monochrome_logs ? '' : "\033[0m" - colorcodes['bold'] = monochrome_logs ? '' : "\033[1m" - colorcodes['dim'] = monochrome_logs ? '' : "\033[2m" - colorcodes['underlined'] = monochrome_logs ? '' : "\033[4m" - colorcodes['blink'] = monochrome_logs ? '' : "\033[5m" - colorcodes['reverse'] = monochrome_logs ? '' : "\033[7m" - colorcodes['hidden'] = monochrome_logs ? '' : "\033[8m" - - // Regular Colors - colorcodes['black'] = monochrome_logs ? '' : "\033[0;30m" - colorcodes['red'] = monochrome_logs ? '' : "\033[0;31m" - colorcodes['green'] = monochrome_logs ? '' : "\033[0;32m" - colorcodes['yellow'] = monochrome_logs ? '' : "\033[0;33m" - colorcodes['blue'] = monochrome_logs ? '' : "\033[0;34m" - colorcodes['purple'] = monochrome_logs ? '' : "\033[0;35m" - colorcodes['cyan'] = monochrome_logs ? '' : "\033[0;36m" - colorcodes['white'] = monochrome_logs ? '' : "\033[0;37m" - - // Bold - colorcodes['bblack'] = monochrome_logs ? '' : "\033[1;30m" - colorcodes['bred'] = monochrome_logs ? '' : "\033[1;31m" - colorcodes['bgreen'] = monochrome_logs ? '' : "\033[1;32m" - colorcodes['byellow'] = monochrome_logs ? '' : "\033[1;33m" - colorcodes['bblue'] = monochrome_logs ? '' : "\033[1;34m" - colorcodes['bpurple'] = monochrome_logs ? '' : "\033[1;35m" - colorcodes['bcyan'] = monochrome_logs ? '' : "\033[1;36m" - colorcodes['bwhite'] = monochrome_logs ? '' : "\033[1;37m" - - // Underline - colorcodes['ublack'] = monochrome_logs ? '' : "\033[4;30m" - colorcodes['ured'] = monochrome_logs ? '' : "\033[4;31m" - colorcodes['ugreen'] = monochrome_logs ? '' : "\033[4;32m" - colorcodes['uyellow'] = monochrome_logs ? '' : "\033[4;33m" - colorcodes['ublue'] = monochrome_logs ? '' : "\033[4;34m" - colorcodes['upurple'] = monochrome_logs ? '' : "\033[4;35m" - colorcodes['ucyan'] = monochrome_logs ? '' : "\033[4;36m" - colorcodes['uwhite'] = monochrome_logs ? '' : "\033[4;37m" - - // High Intensity - colorcodes['iblack'] = monochrome_logs ? '' : "\033[0;90m" - colorcodes['ired'] = monochrome_logs ? '' : "\033[0;91m" - colorcodes['igreen'] = monochrome_logs ? '' : "\033[0;92m" - colorcodes['iyellow'] = monochrome_logs ? '' : "\033[0;93m" - colorcodes['iblue'] = monochrome_logs ? '' : "\033[0;94m" - colorcodes['ipurple'] = monochrome_logs ? '' : "\033[0;95m" - colorcodes['icyan'] = monochrome_logs ? '' : "\033[0;96m" - colorcodes['iwhite'] = monochrome_logs ? '' : "\033[0;97m" - - // Bold High Intensity - colorcodes['biblack'] = monochrome_logs ? '' : "\033[1;90m" - colorcodes['bired'] = monochrome_logs ? '' : "\033[1;91m" - colorcodes['bigreen'] = monochrome_logs ? '' : "\033[1;92m" - colorcodes['biyellow'] = monochrome_logs ? '' : "\033[1;93m" - colorcodes['biblue'] = monochrome_logs ? '' : "\033[1;94m" - colorcodes['bipurple'] = monochrome_logs ? '' : "\033[1;95m" - colorcodes['bicyan'] = monochrome_logs ? '' : "\033[1;96m" - colorcodes['biwhite'] = monochrome_logs ? '' : "\033[1;97m" - - return colorcodes - } - - // - // Does what is says on the tin - // - public static String dashedLine(monochrome_logs) { - Map colors = logColours(monochrome_logs) - return "-${colors.dim}----------------------------------------------------${colors.reset}-" - } - - // - // nf-core logo - // - public static String logo(workflow, monochrome_logs) { - Map colors = logColours(monochrome_logs) - String workflow_version = NfcoreTemplate.version(workflow) - String.format( - """\n - ${dashedLine(monochrome_logs)} - ${colors.green},--.${colors.black}/${colors.green},-.${colors.reset} - ${colors.blue} ___ __ __ __ ___ ${colors.green}/,-._.--~\'${colors.reset} - ${colors.blue} |\\ | |__ __ / ` / \\ |__) |__ ${colors.yellow}} {${colors.reset} - ${colors.blue} | \\| | \\__, \\__/ | \\ |___ ${colors.green}\\`-._,-`-,${colors.reset} - ${colors.green}`._,._,\'${colors.reset} - ${colors.purple} ${workflow.manifest.name} ${workflow_version}${colors.reset} - ${dashedLine(monochrome_logs)} - """.stripIndent() - ) - } -} diff --git a/lib/Utils.groovy b/lib/Utils.groovy deleted file mode 100644 index 8d030f4e..00000000 --- a/lib/Utils.groovy +++ /dev/null @@ -1,47 +0,0 @@ -// -// This file holds several Groovy functions that could be useful for any Nextflow pipeline -// - -import org.yaml.snakeyaml.Yaml - -class Utils { - - // - // When running with -profile conda, warn if channels have not been set-up appropriately - // - public static void checkCondaChannels(log) { - Yaml parser = new Yaml() - def channels = [] - try { - def config = parser.load("conda config --show channels".execute().text) - channels = config.channels - } catch(NullPointerException | IOException e) { - log.warn "Could not verify conda channel configuration." - return - } - - // Check that all channels are present - // This channel list is ordered by required channel priority. - def required_channels_in_order = ['conda-forge', 'bioconda', 'defaults'] - def channels_missing = ((required_channels_in_order as Set) - (channels as Set)) as Boolean - - // Check that they are in the right order - def channel_priority_violation = false - def n = required_channels_in_order.size() - for (int i = 0; i < n - 1; i++) { - channel_priority_violation |= !(channels.indexOf(required_channels_in_order[i]) < channels.indexOf(required_channels_in_order[i+1])) - } - - if (channels_missing | channel_priority_violation) { - log.warn "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + - " There is a problem with your Conda configuration!\n\n" + - " You will need to set-up the conda-forge and bioconda channels correctly.\n" + - " Please refer to https://bioconda.github.io/\n" + - " The observed channel order is \n" + - " ${channels}\n" + - " but the following channel order is required:\n" + - " ${required_channels_in_order}\n" + - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - } - } -} diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy deleted file mode 100755 index e4d0a286..00000000 --- a/lib/WorkflowMain.groovy +++ /dev/null @@ -1,77 +0,0 @@ -// -// This file holds several functions specific to the main.nf workflow in the nf-core/scrnaseq pipeline -// - -import nextflow.Nextflow - -class WorkflowMain { - - // - // Citation string for pipeline - // - public static String citation(workflow) { - return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + - // TODO nf-core: Add Zenodo DOI for pipeline after first release - //"* The pipeline\n" + - //" https://doi.org/10.5281/zenodo.XXXXXXX\n\n" + - "* The nf-core framework\n" + - " https://doi.org/10.1038/s41587-020-0439-x\n\n" + - "* Software dependencies\n" + - " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" - } - - - // - // Validate parameters and print summary to screen - // - public static void initialise(workflow, params, log, args) { - - // Print workflow version and exit on --version - if (params.version) { - String workflow_version = NfcoreTemplate.version(workflow) - log.info "${workflow.manifest.name} ${workflow_version}" - System.exit(0) - } - - // Check that a -profile or Nextflow config has been provided to run the pipeline - NfcoreTemplate.checkConfigProvided(workflow, log) - // Check that the profile doesn't contain spaces and doesn't end with a trailing comma - checkProfile(workflow.profile, args, log) - - // Check that conda channels are set-up correctly - if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) { - Utils.checkCondaChannels(log) - } - - // Check AWS batch settings - NfcoreTemplate.awsBatch(workflow, params) - - // Check input has been provided - if (!params.input) { - Nextflow.error("Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'") - } - } - // - // Get attribute from genome config file e.g. fasta - // - public static Object getGenomeAttribute(params, attribute) { - if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) { - if (params.genomes[ params.genome ].containsKey(attribute)) { - return params.genomes[ params.genome ][ attribute ] - } - } - return null - } - - // - // Exit pipeline if --profile contains spaces - // - private static void checkProfile(profile, args, log) { - if (profile.endsWith(',')) { - Nextflow.error "Profile cannot end with a trailing comma. Please remove the comma from the end of the profile string.\nHint: A common mistake is to provide multiple values to `-profile` separated by spaces. Please use commas to separate profiles instead,e.g., `-profile docker,test`." - } - if (args[0]) { - log.warn "nf-core pipelines do not accept positional arguments. The positional argument `${args[0]}` has been detected.\n Hint: A common mistake is to provide multiple values to `-profile` separated by spaces. Please use commas to separate profiles instead,e.g., `-profile docker,test`." - } - } -} diff --git a/lib/WorkflowScrnaseq.groovy b/lib/WorkflowScrnaseq.groovy deleted file mode 100755 index 04860c20..00000000 --- a/lib/WorkflowScrnaseq.groovy +++ /dev/null @@ -1,122 +0,0 @@ -// -// This file holds several functions specific to the workflow/scrnaseq.nf in the nf-core/scrnaseq pipeline -// - -import nextflow.Nextflow -import groovy.text.SimpleTemplateEngine - -class WorkflowScrnaseq { - - // - // Check and validate parameters - // - public static void initialise(params, log) { - - genomeExistsError(params, log) - - - if (!params.fasta) { - Nextflow.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." - } - } - - // - // Get workflow summary for MultiQC - // - public static String paramsSummaryMultiqc(workflow, summary) { - String summary_section = '' - for (group in summary.keySet()) { - def group_params = summary.get(group) // This gets the parameters of that particular group - if (group_params) { - summary_section += "

$group

\n" - summary_section += "
\n" - for (param in group_params.keySet()) { - summary_section += "
$param
${group_params.get(param) ?: 'N/A'}
\n" - } - summary_section += "
\n" - } - } - - String yaml_file_text = "id: '${workflow.manifest.name.replace('/','-')}-summary'\n" - yaml_file_text += "description: ' - this information is collected when the pipeline is started.'\n" - yaml_file_text += "section_name: '${workflow.manifest.name} Workflow Summary'\n" - yaml_file_text += "section_href: 'https://github.com/${workflow.manifest.name}'\n" - yaml_file_text += "plot_type: 'html'\n" - yaml_file_text += "data: |\n" - yaml_file_text += "${summary_section}" - return yaml_file_text - } - - // - // Generate methods description for MultiQC - // - - public static String toolCitationText(params) { - - // TODO nf-core: Optionally add in-text citation tools to this list. - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "", - // Uncomment function in methodsDescriptionText to render in MultiQC report - def citation_text = [ - "Tools used in the workflow included:", - "FastQC (Andrews 2010),", - "MultiQC (Ewels et al. 2016)", - "." - ].join(' ').trim() - - return citation_text - } - - public static String toolBibliographyText(params) { - - // TODO Optionally add bibliographic entries to this list. - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "
  • Author (2023) Pub name, Journal, DOI
    • " : "", - // Uncomment function in methodsDescriptionText to render in MultiQC report - def reference_text = [ - "
  • Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).
    • ", - "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354
    • " - ].join(' ').trim() - - return reference_text - } - - public static String methodsDescriptionText(run_workflow, mqc_methods_yaml, params) { - // Convert to a named map so can be used as with familar NXF ${workflow} variable syntax in the MultiQC YML file - def meta = [:] - meta.workflow = run_workflow.toMap() - meta["manifest_map"] = run_workflow.manifest.toMap() - - // Pipeline DOI - meta["doi_text"] = meta.manifest_map.doi ? "(doi: ${meta.manifest_map.doi})" : "" - meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " - - // Tool references - meta["tool_citations"] = "" - meta["tool_bibliography"] = "" - - // TODO Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled! - //meta["tool_citations"] = toolCitationText(params).replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") - //meta["tool_bibliography"] = toolBibliographyText(params) - - - def methods_text = mqc_methods_yaml.text - - def engine = new SimpleTemplateEngine() - def description_html = engine.createTemplate(methods_text).make(meta) - - return description_html - } - - // - // Exit pipeline if incorrect --genome key provided - // - private static void genomeExistsError(params, log) { - if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + - " Genome '${params.genome}' not found in any config files provided to the pipeline.\n" + - " Currently, the available genome keys are:\n" + - " ${params.genomes.keySet().join(", ")}\n" + - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - Nextflow.error(error_string) - } - } -} diff --git a/main.nf b/main.nf index dd6b9fbc..fe1b3bad 100644 --- a/main.nf +++ b/main.nf @@ -13,66 +13,96 @@ nextflow.enable.dsl = 2 /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - GENOME PARAMETER VALUES + IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -// TODO nf-core: Remove this line if you don't need a FASTA file -// This is an example of how to use getGenomeAttribute() to fetch parameters -// from igenomes.config using `--genome` -params.fasta = WorkflowMain.getGenomeAttribute(params, 'fasta') +include { SCRNASEQ } from './workflows/scrnaseq' +include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_scrnaseq_pipeline' +include { PIPELINE_COMPLETION } from './subworkflows/local/utils_nfcore_scrnaseq_pipeline' + +include { getGenomeAttribute } from './subworkflows/local/utils_nfcore_scrnaseq_pipeline' /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - VALIDATE & PRINT PARAMETER SUMMARY + GENOME PARAMETER VALUES ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { validateParameters; paramsHelp } from 'plugin/nf-validation' - -// Print help message if needed -if (params.help) { - def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) - def citation = '\n' + WorkflowMain.citation(workflow) + '\n' - def String command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker" - log.info logo + paramsHelp(command) + citation + NfcoreTemplate.dashedLine(params.monochrome_logs) - System.exit(0) -} - -// Validate input parameters -if (params.validate_params) { - validateParameters() -} - -WorkflowMain.initialise(workflow, params, log, args) +// TODO nf-core: Remove this line if you don't need a FASTA file +// This is an example of how to use getGenomeAttribute() to fetch parameters +// from igenomes.config using `--genome` +params.fasta = getGenomeAttribute('fasta') /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - NAMED WORKFLOW FOR PIPELINE + NAMED WORKFLOWS FOR PIPELINE ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { SCRNASEQ } from './workflows/scrnaseq' - // -// WORKFLOW: Run main nf-core/scrnaseq analysis pipeline +// WORKFLOW: Run main analysis pipeline depending on type of input // workflow NFCORE_SCRNASEQ { - SCRNASEQ () -} + take: + samplesheet // channel: samplesheet read in from --input + + main: + + // + // WORKFLOW: Run pipeline + // + SCRNASEQ ( + samplesheet + ) + + emit: + multiqc_report = SCRNASEQ.out.multiqc_report // channel: /path/to/multiqc_report.html + +} /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - RUN ALL WORKFLOWS + RUN MAIN WORKFLOW ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -// -// WORKFLOW: Execute a single named workflow for the pipeline -// See: https://github.com/nf-core/rnaseq/issues/619 -// workflow { - NFCORE_SCRNASEQ () + + main: + + // + // SUBWORKFLOW: Run initialisation tasks + // + PIPELINE_INITIALISATION ( + params.version, + params.help, + params.validate_params, + params.monochrome_logs, + args, + params.outdir, + params.input + ) + + // + // WORKFLOW: Run main workflow + // + NFCORE_SCRNASEQ ( + PIPELINE_INITIALISATION.out.samplesheet + ) + + // + // SUBWORKFLOW: Run completion tasks + // + PIPELINE_COMPLETION ( + params.email, + params.email_on_fail, + params.plaintext_email, + params.outdir, + params.monochrome_logs, + params.hook_url, + NFCORE_SCRNASEQ.out.multiqc_report + ) } /* diff --git a/modules.json b/modules.json index 364c63d0..59464672 100644 --- a/modules.json +++ b/modules.json @@ -5,22 +5,36 @@ "https://github.com/nf-core/modules.git": { "modules": { "nf-core": { - "custom/dumpsoftwareversions": { - "branch": "master", - "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", - "installed_by": ["modules"] - }, "fastqc": { "branch": "master", - "git_sha": "c9488585ce7bd35ccd2a30faa2371454c8112fb9", + "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", "installed_by": ["modules"] }, "multiqc": { "branch": "master", - "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", + "git_sha": "ccacf6f5de6df3bc6d73b665c1fd2933d8bbc290", "installed_by": ["modules"] } } + }, + "subworkflows": { + "nf-core": { + "utils_nextflow_pipeline": { + "branch": "master", + "git_sha": "cd08c91373cd00a73255081340e4914485846ba1", + "installed_by": ["subworkflows"] + }, + "utils_nfcore_pipeline": { + "branch": "master", + "git_sha": "262b17ed2aad591039f914951659177e6c39a8d8", + "installed_by": ["subworkflows"] + }, + "utils_nfvalidation_plugin": { + "branch": "master", + "git_sha": "cd08c91373cd00a73255081340e4914485846ba1", + "installed_by": ["subworkflows"] + } + } } } } diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf deleted file mode 100644 index d3934fdd..00000000 --- a/modules/local/samplesheet_check.nf +++ /dev/null @@ -1,31 +0,0 @@ -process SAMPLESHEET_CHECK { - tag "$samplesheet" - label 'process_single' - - conda "conda-forge::python=3.8.3" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'biocontainers/python:3.8.3' }" - - input: - path samplesheet - - output: - path '*.csv' , emit: csv - path "versions.yml", emit: versions - - when: - task.ext.when == null || task.ext.when - - script: // This script is bundled with the pipeline, in nf-core/scrnaseq/bin/ - """ - check_samplesheet.py \\ - $samplesheet \\ - samplesheet.valid.csv - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - python: \$(python --version | sed 's/Python //g') - END_VERSIONS - """ -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/environment.yml b/modules/nf-core/custom/dumpsoftwareversions/environment.yml deleted file mode 100644 index 9b3272bc..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/environment.yml +++ /dev/null @@ -1,7 +0,0 @@ -name: custom_dumpsoftwareversions -channels: - - conda-forge - - bioconda - - defaults -dependencies: - - bioconda::multiqc=1.19 diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf deleted file mode 100644 index f2187611..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ /dev/null @@ -1,24 +0,0 @@ -process CUSTOM_DUMPSOFTWAREVERSIONS { - label 'process_single' - - // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container - conda "${moduleDir}/environment.yml" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.19--pyhdfd78af_0' : - 'biocontainers/multiqc:1.19--pyhdfd78af_0' }" - - input: - path versions - - output: - path "software_versions.yml" , emit: yml - path "software_versions_mqc.yml", emit: mqc_yml - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - template 'dumpsoftwareversions.py' -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/meta.yml b/modules/nf-core/custom/dumpsoftwareversions/meta.yml deleted file mode 100644 index 5f15a5fd..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/meta.yml +++ /dev/null @@ -1,37 +0,0 @@ -# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json -name: custom_dumpsoftwareversions -description: Custom module used to dump software versions within the nf-core pipeline template -keywords: - - custom - - dump - - version -tools: - - custom: - description: Custom module used to dump software versions within the nf-core pipeline template - homepage: https://github.com/nf-core/tools - documentation: https://github.com/nf-core/tools - licence: ["MIT"] -input: - - versions: - type: file - description: YML file containing software versions - pattern: "*.yml" -output: - - yml: - type: file - description: Standard YML file containing software versions - pattern: "software_versions.yml" - - mqc_yml: - type: file - description: MultiQC custom content YML file containing software versions - pattern: "software_versions_mqc.yml" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@drpatelh" - - "@grst" -maintainers: - - "@drpatelh" - - "@grst" diff --git a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py deleted file mode 100755 index e55b8d43..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py +++ /dev/null @@ -1,102 +0,0 @@ -#!/usr/bin/env python - - -"""Provide functions to merge multiple versions.yml files.""" - - -import platform -from textwrap import dedent - -import yaml - - -def _make_versions_html(versions): - """Generate a tabular HTML output of all versions for MultiQC.""" - html = [ - dedent( - """\\ - - - - - - - - - - """ - ) - ] - for process, tmp_versions in sorted(versions.items()): - html.append("") - for i, (tool, version) in enumerate(sorted(tmp_versions.items())): - html.append( - dedent( - f"""\\ - - - - - - """ - ) - ) - html.append("") - html.append("
    Process Name Software Version
    {process if (i == 0) else ''}{tool}{version}
    ") - return "\\n".join(html) - - -def main(): - """Load all version files and generate merged output.""" - versions_this_module = {} - versions_this_module["${task.process}"] = { - "python": platform.python_version(), - "yaml": yaml.__version__, - } - - with open("$versions") as f: - versions_by_process = yaml.load(f, Loader=yaml.BaseLoader) | versions_this_module - - # aggregate versions by the module name (derived from fully-qualified process name) - versions_by_module = {} - for process, process_versions in versions_by_process.items(): - module = process.split(":")[-1] - try: - if versions_by_module[module] != process_versions: - raise AssertionError( - "We assume that software versions are the same between all modules. " - "If you see this error-message it means you discovered an edge-case " - "and should open an issue in nf-core/tools. " - ) - except KeyError: - versions_by_module[module] = process_versions - - versions_by_module["Workflow"] = { - "Nextflow": "$workflow.nextflow.version", - "$workflow.manifest.name": "$workflow.manifest.version", - } - - versions_mqc = { - "id": "software_versions", - "section_name": "${workflow.manifest.name} Software Versions", - "section_href": "https://github.com/${workflow.manifest.name}", - "plot_type": "html", - "description": "are collected at run time from the software output.", - "data": _make_versions_html(versions_by_module), - } - - with open("software_versions.yml", "w") as f: - yaml.dump(versions_by_module, f, default_flow_style=False) - with open("software_versions_mqc.yml", "w") as f: - yaml.dump(versions_mqc, f, default_flow_style=False) - - with open("versions.yml", "w") as f: - yaml.dump(versions_this_module, f, default_flow_style=False) - - -if __name__ == "__main__": - main() diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test deleted file mode 100644 index b1e1630b..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test +++ /dev/null @@ -1,43 +0,0 @@ -nextflow_process { - - name "Test Process CUSTOM_DUMPSOFTWAREVERSIONS" - script "../main.nf" - process "CUSTOM_DUMPSOFTWAREVERSIONS" - tag "modules" - tag "modules_nfcore" - tag "custom" - tag "dumpsoftwareversions" - tag "custom/dumpsoftwareversions" - - test("Should run without failures") { - when { - process { - """ - def tool1_version = ''' - TOOL1: - tool1: 0.11.9 - '''.stripIndent() - - def tool2_version = ''' - TOOL2: - tool2: 1.9 - '''.stripIndent() - - input[0] = Channel.of(tool1_version, tool2_version).collectFile() - """ - } - } - - then { - assertAll( - { assert process.success }, - { assert snapshot( - process.out.versions, - file(process.out.mqc_yml[0]).readLines()[0..10], - file(process.out.yml[0]).readLines()[0..7] - ).match() - } - ) - } - } -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap deleted file mode 100644 index 5f59a936..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap +++ /dev/null @@ -1,33 +0,0 @@ -{ - "Should run without failures": { - "content": [ - [ - "versions.yml:md5,76d454d92244589d32455833f7c1ba6d" - ], - [ - "data: \"\\n\\n \\n \\n \\n \\n \\n \\n \\n\\", - " \\n\\n\\n \\n \\n\\", - " \\ \\n\\n\\n\\n \\n \\", - " \\ \\n \\n\\n\\n\\n\\", - " \\n\\n \\n \\n\\", - " \\ \\n\\n\\n\\n\\n\\n \\n\\", - " \\ \\n \\n\\n\\n\\n\\", - " \\n\\n \\n \\n\\" - ], - [ - "CUSTOM_DUMPSOFTWAREVERSIONS:", - " python: 3.11.7", - " yaml: 5.4.1", - "TOOL1:", - " tool1: 0.11.9", - "TOOL2:", - " tool2: '1.9'", - "Workflow:" - ] - ], - "timestamp": "2024-01-09T23:01:18.710682" - } -} \ No newline at end of file diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml b/modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml deleted file mode 100644 index 405aa24a..00000000 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/tags.yml +++ /dev/null @@ -1,2 +0,0 @@ -custom/dumpsoftwareversions: - - modules/nf-core/custom/dumpsoftwareversions/** diff --git a/modules/nf-core/fastqc/tests/main.nf.test b/modules/nf-core/fastqc/tests/main.nf.test index 1f21c664..70edae4d 100644 --- a/modules/nf-core/fastqc/tests/main.nf.test +++ b/modules/nf-core/fastqc/tests/main.nf.test @@ -33,7 +33,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_single") } ) } } @@ -63,7 +63,7 @@ nextflow_process { { assert path(process.out.html[0][1][0]).text.contains("") }, { assert path(process.out.html[0][1][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_paired") } ) } } @@ -89,7 +89,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_interleaved") } ) } } @@ -115,7 +115,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_bam") } ) } } @@ -153,7 +153,7 @@ nextflow_process { { assert path(process.out.html[0][1][2]).text.contains("") }, { assert path(process.out.html[0][1][3]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_multiple") } ) } } @@ -179,7 +179,7 @@ nextflow_process { { assert process.out.zip[0][1] ==~ ".*/mysample_fastqc.zip" }, { assert path(process.out.html[0][1]).text.contains("") }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("fastqc_versions_custom_prefix") } ) } } @@ -204,7 +204,7 @@ nextflow_process { { assert process.success }, { assert snapshot(process.out.html.collect { file(it[1]).getName() } + process.out.zip.collect { file(it[1]).getName() } + - process.out.versions ).match() } + process.out.versions ).match("fastqc_stub") } ) } } diff --git a/modules/nf-core/fastqc/tests/main.nf.test.snap b/modules/nf-core/fastqc/tests/main.nf.test.snap index 5d624bb8..86f7c311 100644 --- a/modules/nf-core/fastqc/tests/main.nf.test.snap +++ b/modules/nf-core/fastqc/tests/main.nf.test.snap @@ -1,5 +1,17 @@ { - "sarscov2 single-end [fastq] - stub": { + "fastqc_versions_interleaved": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:40:07.293713" + }, + "fastqc_stub": { "content": [ [ "test.html", @@ -7,14 +19,70 @@ "versions.yml:md5,e1cc25ca8af856014824abd842e93978" ] ], - "timestamp": "2024-01-17T18:40:57.254299" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:31:01.425198" + }, + "fastqc_versions_multiple": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:40:55.797907" + }, + "fastqc_versions_bam": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:40:26.795862" + }, + "fastqc_versions_single": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:39:27.043675" + }, + "fastqc_versions_paired": { + "content": [ + [ + "versions.yml:md5,e1cc25ca8af856014824abd842e93978" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:39:47.584191" }, - "versions": { + "fastqc_versions_custom_prefix": { "content": [ [ "versions.yml:md5,e1cc25ca8af856014824abd842e93978" ] ], - "timestamp": "2024-01-17T18:36:50.033627" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-01-31T17:41:14.576531" } } \ No newline at end of file diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml index 7625b752..2212096a 100644 --- a/modules/nf-core/multiqc/environment.yml +++ b/modules/nf-core/multiqc/environment.yml @@ -4,4 +4,4 @@ channels: - bioconda - defaults dependencies: - - bioconda::multiqc=1.19 + - bioconda::multiqc=1.20 diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 1b9f7c43..354f4430 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -3,8 +3,8 @@ process MULTIQC { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.19--pyhdfd78af_0' : - 'biocontainers/multiqc:1.19--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.20--pyhdfd78af_0' : + 'biocontainers/multiqc:1.20--pyhdfd78af_0' }" input: path multiqc_files, stageAs: "?/*" diff --git a/modules/nf-core/multiqc/tests/main.nf.test b/modules/nf-core/multiqc/tests/main.nf.test index d0438eda..f1c4242e 100644 --- a/modules/nf-core/multiqc/tests/main.nf.test +++ b/modules/nf-core/multiqc/tests/main.nf.test @@ -3,6 +3,7 @@ nextflow_process { name "Test Process MULTIQC" script "../main.nf" process "MULTIQC" + tag "modules" tag "modules_nfcore" tag "multiqc" @@ -12,7 +13,7 @@ nextflow_process { when { process { """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) + input[0] = Channel.of(file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastqc/test_fastqc.zip', checkIfExists: true)) input[1] = [] input[2] = [] input[3] = [] @@ -25,7 +26,7 @@ nextflow_process { { assert process.success }, { assert process.out.report[0] ==~ ".*/multiqc_report.html" }, { assert process.out.data[0] ==~ ".*/multiqc_data" }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("multiqc_versions_single") } ) } @@ -36,7 +37,7 @@ nextflow_process { when { process { """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) + input[0] = Channel.of(file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastqc/test_fastqc.zip', checkIfExists: true)) input[1] = Channel.of(file("https://github.com/nf-core/tools/raw/dev/nf_core/pipeline-template/assets/multiqc_config.yml", checkIfExists: true)) input[2] = [] input[3] = [] @@ -49,7 +50,7 @@ nextflow_process { { assert process.success }, { assert process.out.report[0] ==~ ".*/multiqc_report.html" }, { assert process.out.data[0] ==~ ".*/multiqc_data" }, - { assert snapshot(process.out.versions).match("versions") } + { assert snapshot(process.out.versions).match("multiqc_versions_config") } ) } } @@ -61,7 +62,7 @@ nextflow_process { when { process { """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) + input[0] = Channel.of(file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastqc/test_fastqc.zip', checkIfExists: true)) input[1] = [] input[2] = [] input[3] = [] @@ -75,7 +76,7 @@ nextflow_process { { assert snapshot(process.out.report.collect { file(it).getName() } + process.out.data.collect { file(it).getName() } + process.out.plots.collect { file(it).getName() } + - process.out.versions ).match() } + process.out.versions ).match("multiqc_stub") } ) } diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap index d37e7304..c204b488 100644 --- a/modules/nf-core/multiqc/tests/main.nf.test.snap +++ b/modules/nf-core/multiqc/tests/main.nf.test.snap @@ -1,21 +1,41 @@ { - "versions": { + "multiqc_versions_single": { "content": [ [ - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" ] ], - "timestamp": "2024-01-09T23:02:49.911994" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-14T09:28:51.744211298" }, - "sarscov2 single-end [fastqc] - stub": { + "multiqc_stub": { "content": [ [ "multiqc_report.html", "multiqc_data", "multiqc_plots", - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" ] ], - "timestamp": "2024-01-09T23:03:14.524346" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-14T09:29:28.847433492" + }, + "multiqc_versions_config": { + "content": [ + [ + "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-14T09:29:13.223621555" } } \ No newline at end of file diff --git a/nextflow.config b/nextflow.config index 5ece77c6..9508cefa 100644 --- a/nextflow.config +++ b/nextflow.config @@ -16,9 +16,7 @@ params { genome = null igenomes_base = 's3://ngi-igenomes/igenomes/' igenomes_ignore = false - - - // MultiQC options + fasta = null// MultiQC options multiqc_config = null multiqc_title = null multiqc_logo = null @@ -43,7 +41,6 @@ params { custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" config_profile_contact = null config_profile_url = null - // Max resource options // Defaults only, expecting to be overwritten diff --git a/nextflow_schema.json b/nextflow_schema.json index 37c2128c..233b47d4 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -16,6 +16,7 @@ "type": "string", "format": "file-path", "exists": true, + "schema": "assets/schema_input.json", "mimetype": "text/csv", "pattern": "^\\S+\\.csv$", "description": "Path to comma-separated file containing information about the samples in the experiment.", diff --git a/pyproject.toml b/pyproject.toml index 7d08e1c8..56110621 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -3,11 +3,13 @@ [tool.ruff] line-length = 120 target-version = "py38" -select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"] cache-dir = "~/.cache/ruff" -[tool.ruff.isort] +[tool.ruff.lint] +select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"] + +[tool.ruff.lint.isort] known-first-party = ["nf_core"] -[tool.ruff.per-file-ignores] +[tool.ruff.lint.per-file-ignores] "__init__.py" = ["E402", "F401"] diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf deleted file mode 100644 index 0aecf87f..00000000 --- a/subworkflows/local/input_check.nf +++ /dev/null @@ -1,44 +0,0 @@ -// -// Check input samplesheet and get read channels -// - -include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check' - -workflow INPUT_CHECK { - take: - samplesheet // file: /path/to/samplesheet.csv - - main: - SAMPLESHEET_CHECK ( samplesheet ) - .csv - .splitCsv ( header:true, sep:',' ) - .map { create_fastq_channel(it) } - .set { reads } - - emit: - reads // channel: [ val(meta), [ reads ] ] - versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ] -} - -// Function to get list of [ meta, [ fastq_1, fastq_2 ] ] -def create_fastq_channel(LinkedHashMap row) { - // create meta map - def meta = [:] - meta.id = row.sample - meta.single_end = row.single_end.toBoolean() - - // add path(s) of the fastq file(s) to the meta map - def fastq_meta = [] - if (!file(row.fastq_1).exists()) { - exit 1, "ERROR: Please check input samplesheet -> Read 1 FastQ file does not exist!\n${row.fastq_1}" - } - if (meta.single_end) { - fastq_meta = [ meta, [ file(row.fastq_1) ] ] - } else { - if (!file(row.fastq_2).exists()) { - exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}" - } - fastq_meta = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ] - } - return fastq_meta -} diff --git a/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf b/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf new file mode 100644 index 00000000..dc90ad90 --- /dev/null +++ b/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf @@ -0,0 +1,247 @@ +// +// Subworkflow with functionality specific to the nf-core/pipeline pipeline +// + +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +*/ + +include { UTILS_NFVALIDATION_PLUGIN } from '../../nf-core/utils_nfvalidation_plugin' +include { paramsSummaryMap } from 'plugin/nf-validation' +include { fromSamplesheet } from 'plugin/nf-validation' +include { UTILS_NEXTFLOW_PIPELINE } from '../../nf-core/utils_nextflow_pipeline' +include { completionEmail } from '../../nf-core/utils_nfcore_pipeline' +include { completionSummary } from '../../nf-core/utils_nfcore_pipeline' +include { dashedLine } from '../../nf-core/utils_nfcore_pipeline' +include { nfCoreLogo } from '../../nf-core/utils_nfcore_pipeline' +include { imNotification } from '../../nf-core/utils_nfcore_pipeline' +include { UTILS_NFCORE_PIPELINE } from '../../nf-core/utils_nfcore_pipeline' +include { workflowCitation } from '../../nf-core/utils_nfcore_pipeline' + +/* +======================================================================================== + SUBWORKFLOW TO INITIALISE PIPELINE +======================================================================================== +*/ + +workflow PIPELINE_INITIALISATION { + + take: + version // boolean: Display version and exit + help // boolean: Display help text + validate_params // boolean: Boolean whether to validate parameters against the schema at runtime + monochrome_logs // boolean: Do not use coloured log outputs + nextflow_cli_args // array: List of positional nextflow CLI args + outdir // string: The output directory where the results will be saved + input // string: Path to input samplesheet + + main: + + ch_versions = Channel.empty() + + // + // Print version and exit if required and dump pipeline parameters to JSON file + // + UTILS_NEXTFLOW_PIPELINE ( + version, + true, + outdir, + workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1 + ) + + // + // Validate parameters and generate parameter summary to stdout + // + pre_help_text = nfCoreLogo(monochrome_logs) + post_help_text = '\n' + workflowCitation() + '\n' + dashedLine(monochrome_logs) + def String workflow_command = "nextflow run ${workflow.manifest.name} -profile --input samplesheet.csv --outdir " + UTILS_NFVALIDATION_PLUGIN ( + help, + workflow_command, + pre_help_text, + post_help_text, + validate_params, + "nextflow_schema.json" + ) + + // + // Check config provided to the pipeline + // + UTILS_NFCORE_PIPELINE ( + nextflow_cli_args + ) + // + // Custom validation for pipeline parameters + // + validateInputParameters() + + // + // Create channel from input file provided through params.input + // + Channel + .fromSamplesheet("input") + .map { + meta, fastq_1, fastq_2 -> + if (!fastq_2) { + return [ meta.id, meta + [ single_end:true ], [ fastq_1 ] ] + } else { + return [ meta.id, meta + [ single_end:false ], [ fastq_1, fastq_2 ] ] + } + } + .groupTuple() + .map { + validateInputSamplesheet(it) + } + .map { + meta, fastqs -> + return [ meta, fastqs.flatten() ] + } + .set { ch_samplesheet } + + emit: + samplesheet = ch_samplesheet + versions = ch_versions +} + +/* +======================================================================================== + SUBWORKFLOW FOR PIPELINE COMPLETION +======================================================================================== +*/ + +workflow PIPELINE_COMPLETION { + + take: + email // string: email address + email_on_fail // string: email address sent on pipeline failure + plaintext_email // boolean: Send plain-text email instead of HTML + outdir // path: Path to output directory where results will be published + monochrome_logs // boolean: Disable ANSI colour codes in log output + hook_url // string: hook URL for notifications + multiqc_report // string: Path to MultiQC report + + main: + + summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json") + + // + // Completion email and summary + // + workflow.onComplete { + if (email || email_on_fail) { + completionEmail(summary_params, email, email_on_fail, plaintext_email, outdir, monochrome_logs, multiqc_report.toList()) + } + + completionSummary(monochrome_logs) + + if (hook_url) { + imNotification(summary_params, hook_url) + } + } +} + +/* +======================================================================================== + FUNCTIONS +======================================================================================== +*/ +// +// Check and validate pipeline parameters +// +def validateInputParameters() { + genomeExistsError() +}// +// Validate channels from input samplesheet +// +def validateInputSamplesheet(input) { + def (metas, fastqs) = input[1..2] + + // Check that multiple runs of the same sample are of the same datatype i.e. single-end / paired-end + def endedness_ok = metas.collect{ it.single_end }.unique().size == 1 + if (!endedness_ok) { + error("Please check input samplesheet -> Multiple runs of a sample must be of the same datatype i.e. single-end or paired-end: ${metas[0].id}") + } + + return [ metas[0], fastqs ] +} +// +// Get attribute from genome config file e.g. fasta +// +def getGenomeAttribute(attribute) { + if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) { + if (params.genomes[ params.genome ].containsKey(attribute)) { + return params.genomes[ params.genome ][ attribute ] + } + } + return null +} + +// +// Exit pipeline if incorrect --genome key provided +// +def genomeExistsError() { + if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { + def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + + " Genome '${params.genome}' not found in any config files provided to the pipeline.\n" + + " Currently, the available genome keys are:\n" + + " ${params.genomes.keySet().join(", ")}\n" + + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" + error(error_string) + } +}// +// Generate methods description for MultiQC +// +def toolCitationText() { + // TODO nf-core: Optionally add in-text citation tools to this list. + // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "", + // Uncomment function in methodsDescriptionText to render in MultiQC report + def citation_text = [ + "Tools used in the workflow included:", + "FastQC (Andrews 2010),", + "MultiQC (Ewels et al. 2016)", + "." + ].join(' ').trim() + + return citation_text +} + +def toolBibliographyText() { + // TODO nf-core: Optionally add bibliographic entries to this list. + // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "
  • Author (2023) Pub name, Journal, DOI
    • " : "", + // Uncomment function in methodsDescriptionText to render in MultiQC report + def reference_text = [ + "
  • Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).
    • ", + "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. doi: /10.1093/bioinformatics/btw354
    • " + ].join(' ').trim() + + return reference_text +} + +def methodsDescriptionText(mqc_methods_yaml) { + // Convert to a named map so can be used as with familar NXF ${workflow} variable syntax in the MultiQC YML file + def meta = [:] + meta.workflow = workflow.toMap() + meta["manifest_map"] = workflow.manifest.toMap() + + // Pipeline DOI + meta["doi_text"] = meta.manifest_map.doi ? "(doi: ${meta.manifest_map.doi})" : "" + meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " + + // Tool references + meta["tool_citations"] = "" + meta["tool_bibliography"] = "" + + // TODO nf-core: Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled! + // meta["tool_citations"] = toolCitationText().replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") + // meta["tool_bibliography"] = toolBibliographyText() + + + def methods_text = mqc_methods_yaml.text + + def engine = new groovy.text.SimpleTemplateEngine() + def description_html = engine.createTemplate(methods_text).make(meta) + + return description_html.toString() +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/main.nf b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf new file mode 100644 index 00000000..ac31f28f --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/main.nf @@ -0,0 +1,126 @@ +// +// Subworkflow with functionality that may be useful for any Nextflow pipeline +// + +import org.yaml.snakeyaml.Yaml +import groovy.json.JsonOutput +import nextflow.extension.FilesEx + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NEXTFLOW_PIPELINE { + + take: + print_version // boolean: print version + dump_parameters // boolean: dump parameters + outdir // path: base directory used to publish pipeline results + check_conda_channels // boolean: check conda channels + + main: + + // + // Print workflow version and exit on --version + // + if (print_version) { + log.info "${workflow.manifest.name} ${getWorkflowVersion()}" + System.exit(0) + } + + // + // Dump pipeline parameters to a JSON file + // + if (dump_parameters && outdir) { + dumpParametersToJSON(outdir) + } + + // + // When running with Conda, warn if channels have not been set-up appropriately + // + if (check_conda_channels) { + checkCondaChannels() + } + + emit: + dummy_emit = true +} + +/* +======================================================================================== + FUNCTIONS +======================================================================================== +*/ + +// +// Generate version string +// +def getWorkflowVersion() { + String version_string = "" + if (workflow.manifest.version) { + def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : '' + version_string += "${prefix_v}${workflow.manifest.version}" + } + + if (workflow.commitId) { + def git_shortsha = workflow.commitId.substring(0, 7) + version_string += "-g${git_shortsha}" + } + + return version_string +} + +// +// Dump pipeline parameters to a JSON file +// +def dumpParametersToJSON(outdir) { + def timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') + def filename = "params_${timestamp}.json" + def temp_pf = new File(workflow.launchDir.toString(), ".${filename}") + def jsonStr = JsonOutput.toJson(params) + temp_pf.text = JsonOutput.prettyPrint(jsonStr) + + FilesEx.copyTo(temp_pf.toPath(), "${outdir}/pipeline_info/params_${timestamp}.json") + temp_pf.delete() +} + +// +// When running with -profile conda, warn if channels have not been set-up appropriately +// +def checkCondaChannels() { + Yaml parser = new Yaml() + def channels = [] + try { + def config = parser.load("conda config --show channels".execute().text) + channels = config.channels + } catch(NullPointerException | IOException e) { + log.warn "Could not verify conda channel configuration." + return + } + + // Check that all channels are present + // This channel list is ordered by required channel priority. + def required_channels_in_order = ['conda-forge', 'bioconda', 'defaults'] + def channels_missing = ((required_channels_in_order as Set) - (channels as Set)) as Boolean + + // Check that they are in the right order + def channel_priority_violation = false + def n = required_channels_in_order.size() + for (int i = 0; i < n - 1; i++) { + channel_priority_violation |= !(channels.indexOf(required_channels_in_order[i]) < channels.indexOf(required_channels_in_order[i+1])) + } + + if (channels_missing | channel_priority_violation) { + log.warn "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + + " There is a problem with your Conda configuration!\n\n" + + " You will need to set-up the conda-forge and bioconda channels correctly.\n" + + " Please refer to https://bioconda.github.io/\n" + + " The observed channel order is \n" + + " ${channels}\n" + + " but the following channel order is required:\n" + + " ${required_channels_in_order}\n" + + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" + } +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml b/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml new file mode 100644 index 00000000..e5c3a0a8 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/meta.yml @@ -0,0 +1,38 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NEXTFLOW_PIPELINE" +description: Subworkflow with functionality that may be useful for any Nextflow pipeline +keywords: + - utility + - pipeline + - initialise + - version +components: [] +input: + - print_version: + type: boolean + description: | + Print the version of the pipeline and exit + - dump_parameters: + type: boolean + description: | + Dump the parameters of the pipeline to a JSON file + - output_directory: + type: directory + description: Path to output dir to write JSON file to. + pattern: "results/" + - check_conda_channel: + type: boolean + description: | + Check if the conda channel priority is correct. +output: + - dummy_emit: + type: boolean + description: | + Dummy emit to make nf-core subworkflows lint happy +authors: + - "@adamrtalbot" + - "@drpatelh" +maintainers: + - "@adamrtalbot" + - "@drpatelh" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test new file mode 100644 index 00000000..8ed4310c --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test @@ -0,0 +1,54 @@ + +nextflow_function { + + name "Test Functions" + script "subworkflows/nf-core/utils_nextflow_pipeline/main.nf" + config "subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config" + tag 'subworkflows' + tag 'utils_nextflow_pipeline' + tag 'subworkflows/utils_nextflow_pipeline' + + test("Test Function getWorkflowVersion") { + + function "getWorkflowVersion" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function dumpParametersToJSON") { + + function "dumpParametersToJSON" + + when { + function { + """ + // define inputs of the function here. Example: + input[0] = "$outputDir" + """.stripIndent() + } + } + + then { + assertAll( + { assert function.success } + ) + } + } + + test("Test Function checkCondaChannels") { + + function "checkCondaChannels" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap new file mode 100644 index 00000000..db2030f8 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap @@ -0,0 +1,12 @@ +{ + "Test Function getWorkflowVersion": { + "content": [ + "v9.9.9" + ], + "timestamp": "2024-01-19T11:32:36.031083" + }, + "Test Function checkCondaChannels": { + "content": null, + "timestamp": "2024-01-19T11:32:50.456" + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test new file mode 100644 index 00000000..f7c54bc6 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test @@ -0,0 +1,123 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NEXTFLOW_PIPELINE" + script "../main.nf" + config "subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config" + workflow "UTILS_NEXTFLOW_PIPELINE" + tag 'subworkflows' + tag 'utils_nextflow_pipeline' + tag 'subworkflows/utils_nextflow_pipeline' + + test("Should run no inputs") { + + when { + params { + outdir = "tests/results" + } + workflow { + """ + print_version = false + dump_parameters = false + outdir = null + check_conda_channels = false + + input[0] = print_version + input[1] = dump_parameters + input[2] = outdir + input[3] = check_conda_channels + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should print version") { + + when { + params { + outdir = "tests/results" + } + workflow { + """ + print_version = true + dump_parameters = false + outdir = null + check_conda_channels = false + + input[0] = print_version + input[1] = dump_parameters + input[2] = outdir + input[3] = check_conda_channels + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.stdout.contains("nextflow_workflow v9.9.9") } + ) + } + } + + test("Should dump params") { + + when { + params { + outdir = "$outputDir" + } + workflow { + """ + print_version = false + dump_parameters = true + outdir = params.outdir + check_conda_channels = false + + input[0] = false + input[1] = true + input[2] = params.outdir + input[3] = false + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should not create params JSON if no output directory") { + + when { + params { + outdir = "$outputDir" + } + workflow { + """ + print_version = false + dump_parameters = true + outdir = params.outdir + check_conda_channels = false + + input[0] = false + input[1] = true + input[2] = null + input[3] = false + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config b/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config new file mode 100644 index 00000000..53574ffe --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config @@ -0,0 +1,9 @@ +manifest { + name = 'nextflow_workflow' + author = """nf-core""" + homePage = 'https://127.0.0.1' + description = """Dummy pipeline""" + nextflowVersion = '!>=23.04.0' + version = '9.9.9' + doi = 'https://doi.org/10.5281/zenodo.5070524' +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml b/subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml new file mode 100644 index 00000000..f8476112 --- /dev/null +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/tags.yml @@ -0,0 +1,2 @@ +subworkflows/utils_nextflow_pipeline: + - subworkflows/nf-core/utils_nextflow_pipeline/** diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/main.nf b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf new file mode 100644 index 00000000..a8b55d6f --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/main.nf @@ -0,0 +1,440 @@ +// +// Subworkflow with utility functions specific to the nf-core pipeline template +// + +import org.yaml.snakeyaml.Yaml +import nextflow.extension.FilesEx + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NFCORE_PIPELINE { + + take: + nextflow_cli_args + + main: + valid_config = checkConfigProvided() + checkProfileProvided(nextflow_cli_args) + + emit: + valid_config +} + +/* +======================================================================================== + FUNCTIONS +======================================================================================== +*/ + +// +// Warn if a -profile or Nextflow config has not been provided to run the pipeline +// +def checkConfigProvided() { + valid_config = true + if (workflow.profile == 'standard' && workflow.configFiles.size() <= 1) { + log.warn "[$workflow.manifest.name] You are attempting to run the pipeline without any custom configuration!\n\n" + + "This will be dependent on your local compute environment but can be achieved via one or more of the following:\n" + + " (1) Using an existing pipeline profile e.g. `-profile docker` or `-profile singularity`\n" + + " (2) Using an existing nf-core/configs for your Institution e.g. `-profile crick` or `-profile uppmax`\n" + + " (3) Using your own local custom config e.g. `-c /path/to/your/custom.config`\n\n" + + "Please refer to the quick start section and usage docs for the pipeline.\n " + valid_config = false + } + return valid_config +} + +// +// Exit pipeline if --profile contains spaces +// +def checkProfileProvided(nextflow_cli_args) { + if (workflow.profile.endsWith(',')) { + error "The `-profile` option cannot end with a trailing comma, please remove it and re-run the pipeline!\n" + + "HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.\n" + } + if (nextflow_cli_args[0]) { + log.warn "nf-core pipelines do not accept positional arguments. The positional argument `${nextflow_cli_args[0]}` has been detected.\n" + + "HINT: A common mistake is to provide multiple values separated by spaces e.g. `-profile test, docker`.\n" + } +} + +// +// Citation string for pipeline +// +def workflowCitation() { + return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + + "* The pipeline\n" + + " ${workflow.manifest.doi}\n\n" + + "* The nf-core framework\n" + + " https://doi.org/10.1038/s41587-020-0439-x\n\n" + + "* Software dependencies\n" + + " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" +} + +// +// Generate workflow version string +// +def getWorkflowVersion() { + String version_string = "" + if (workflow.manifest.version) { + def prefix_v = workflow.manifest.version[0] != 'v' ? 'v' : '' + version_string += "${prefix_v}${workflow.manifest.version}" + } + + if (workflow.commitId) { + def git_shortsha = workflow.commitId.substring(0, 7) + version_string += "-g${git_shortsha}" + } + + return version_string +} + +// +// Get software versions for pipeline +// +def processVersionsFromYAML(yaml_file) { + Yaml yaml = new Yaml() + versions = yaml.load(yaml_file).collectEntries { k, v -> [ k.tokenize(':')[-1], v ] } + return yaml.dumpAsMap(versions).trim() +} + +// +// Get workflow version for pipeline +// +def workflowVersionToYAML() { + return """ + Workflow: + $workflow.manifest.name: ${getWorkflowVersion()} + Nextflow: $workflow.nextflow.version + """.stripIndent().trim() +} + +// +// Get channel of software versions used in pipeline in YAML format +// +def softwareVersionsToYAML(ch_versions) { + return ch_versions + .unique() + .map { processVersionsFromYAML(it) } + .unique() + .mix(Channel.of(workflowVersionToYAML())) +} + +// +// Get workflow summary for MultiQC +// +def paramsSummaryMultiqc(summary_params) { + def summary_section = '' + for (group in summary_params.keySet()) { + def group_params = summary_params.get(group) // This gets the parameters of that particular group + if (group_params) { + summary_section += "

    $group

    \n" + summary_section += "
    \n" + for (param in group_params.keySet()) { + summary_section += "
    $param
    ${group_params.get(param) ?: 'N/A'}
    \n" + } + summary_section += "
    \n" + } + } + + String yaml_file_text = "id: '${workflow.manifest.name.replace('/','-')}-summary'\n" + yaml_file_text += "description: ' - this information is collected when the pipeline is started.'\n" + yaml_file_text += "section_name: '${workflow.manifest.name} Workflow Summary'\n" + yaml_file_text += "section_href: 'https://github.com/${workflow.manifest.name}'\n" + yaml_file_text += "plot_type: 'html'\n" + yaml_file_text += "data: |\n" + yaml_file_text += "${summary_section}" + + return yaml_file_text +} + +// +// nf-core logo +// +def nfCoreLogo(monochrome_logs=true) { + Map colors = logColours(monochrome_logs) + String.format( + """\n + ${dashedLine(monochrome_logs)} + ${colors.green},--.${colors.black}/${colors.green},-.${colors.reset} + ${colors.blue} ___ __ __ __ ___ ${colors.green}/,-._.--~\'${colors.reset} + ${colors.blue} |\\ | |__ __ / ` / \\ |__) |__ ${colors.yellow}} {${colors.reset} + ${colors.blue} | \\| | \\__, \\__/ | \\ |___ ${colors.green}\\`-._,-`-,${colors.reset} + ${colors.green}`._,._,\'${colors.reset} + ${colors.purple} ${workflow.manifest.name} ${getWorkflowVersion()}${colors.reset} + ${dashedLine(monochrome_logs)} + """.stripIndent() + ) +} + +// +// Return dashed line +// +def dashedLine(monochrome_logs=true) { + Map colors = logColours(monochrome_logs) + return "-${colors.dim}----------------------------------------------------${colors.reset}-" +} + +// +// ANSII colours used for terminal logging +// +def logColours(monochrome_logs=true) { + Map colorcodes = [:] + + // Reset / Meta + colorcodes['reset'] = monochrome_logs ? '' : "\033[0m" + colorcodes['bold'] = monochrome_logs ? '' : "\033[1m" + colorcodes['dim'] = monochrome_logs ? '' : "\033[2m" + colorcodes['underlined'] = monochrome_logs ? '' : "\033[4m" + colorcodes['blink'] = monochrome_logs ? '' : "\033[5m" + colorcodes['reverse'] = monochrome_logs ? '' : "\033[7m" + colorcodes['hidden'] = monochrome_logs ? '' : "\033[8m" + + // Regular Colors + colorcodes['black'] = monochrome_logs ? '' : "\033[0;30m" + colorcodes['red'] = monochrome_logs ? '' : "\033[0;31m" + colorcodes['green'] = monochrome_logs ? '' : "\033[0;32m" + colorcodes['yellow'] = monochrome_logs ? '' : "\033[0;33m" + colorcodes['blue'] = monochrome_logs ? '' : "\033[0;34m" + colorcodes['purple'] = monochrome_logs ? '' : "\033[0;35m" + colorcodes['cyan'] = monochrome_logs ? '' : "\033[0;36m" + colorcodes['white'] = monochrome_logs ? '' : "\033[0;37m" + + // Bold + colorcodes['bblack'] = monochrome_logs ? '' : "\033[1;30m" + colorcodes['bred'] = monochrome_logs ? '' : "\033[1;31m" + colorcodes['bgreen'] = monochrome_logs ? '' : "\033[1;32m" + colorcodes['byellow'] = monochrome_logs ? '' : "\033[1;33m" + colorcodes['bblue'] = monochrome_logs ? '' : "\033[1;34m" + colorcodes['bpurple'] = monochrome_logs ? '' : "\033[1;35m" + colorcodes['bcyan'] = monochrome_logs ? '' : "\033[1;36m" + colorcodes['bwhite'] = monochrome_logs ? '' : "\033[1;37m" + + // Underline + colorcodes['ublack'] = monochrome_logs ? '' : "\033[4;30m" + colorcodes['ured'] = monochrome_logs ? '' : "\033[4;31m" + colorcodes['ugreen'] = monochrome_logs ? '' : "\033[4;32m" + colorcodes['uyellow'] = monochrome_logs ? '' : "\033[4;33m" + colorcodes['ublue'] = monochrome_logs ? '' : "\033[4;34m" + colorcodes['upurple'] = monochrome_logs ? '' : "\033[4;35m" + colorcodes['ucyan'] = monochrome_logs ? '' : "\033[4;36m" + colorcodes['uwhite'] = monochrome_logs ? '' : "\033[4;37m" + + // High Intensity + colorcodes['iblack'] = monochrome_logs ? '' : "\033[0;90m" + colorcodes['ired'] = monochrome_logs ? '' : "\033[0;91m" + colorcodes['igreen'] = monochrome_logs ? '' : "\033[0;92m" + colorcodes['iyellow'] = monochrome_logs ? '' : "\033[0;93m" + colorcodes['iblue'] = monochrome_logs ? '' : "\033[0;94m" + colorcodes['ipurple'] = monochrome_logs ? '' : "\033[0;95m" + colorcodes['icyan'] = monochrome_logs ? '' : "\033[0;96m" + colorcodes['iwhite'] = monochrome_logs ? '' : "\033[0;97m" + + // Bold High Intensity + colorcodes['biblack'] = monochrome_logs ? '' : "\033[1;90m" + colorcodes['bired'] = monochrome_logs ? '' : "\033[1;91m" + colorcodes['bigreen'] = monochrome_logs ? '' : "\033[1;92m" + colorcodes['biyellow'] = monochrome_logs ? '' : "\033[1;93m" + colorcodes['biblue'] = monochrome_logs ? '' : "\033[1;94m" + colorcodes['bipurple'] = monochrome_logs ? '' : "\033[1;95m" + colorcodes['bicyan'] = monochrome_logs ? '' : "\033[1;96m" + colorcodes['biwhite'] = monochrome_logs ? '' : "\033[1;97m" + + return colorcodes +} + +// +// Attach the multiqc report to email +// +def attachMultiqcReport(multiqc_report) { + def mqc_report = null + try { + if (workflow.success) { + mqc_report = multiqc_report.getVal() + if (mqc_report.getClass() == ArrayList && mqc_report.size() >= 1) { + if (mqc_report.size() > 1) { + log.warn "[$workflow.manifest.name] Found multiple reports from process 'MULTIQC', will use only one" + } + mqc_report = mqc_report[0] + } + } + } catch (all) { + if (multiqc_report) { + log.warn "[$workflow.manifest.name] Could not attach MultiQC report to summary email" + } + } + return mqc_report +} + +// +// Construct and send completion email +// +def completionEmail(summary_params, email, email_on_fail, plaintext_email, outdir, monochrome_logs=true, multiqc_report=null) { + + // Set up the e-mail variables + def subject = "[$workflow.manifest.name] Successful: $workflow.runName" + if (!workflow.success) { + subject = "[$workflow.manifest.name] FAILED: $workflow.runName" + } + + def summary = [:] + for (group in summary_params.keySet()) { + summary << summary_params[group] + } + + def misc_fields = [:] + misc_fields['Date Started'] = workflow.start + misc_fields['Date Completed'] = workflow.complete + misc_fields['Pipeline script file path'] = workflow.scriptFile + misc_fields['Pipeline script hash ID'] = workflow.scriptId + if (workflow.repository) misc_fields['Pipeline repository Git URL'] = workflow.repository + if (workflow.commitId) misc_fields['Pipeline repository Git Commit'] = workflow.commitId + if (workflow.revision) misc_fields['Pipeline Git branch/tag'] = workflow.revision + misc_fields['Nextflow Version'] = workflow.nextflow.version + misc_fields['Nextflow Build'] = workflow.nextflow.build + misc_fields['Nextflow Compile Timestamp'] = workflow.nextflow.timestamp + + def email_fields = [:] + email_fields['version'] = getWorkflowVersion() + email_fields['runName'] = workflow.runName + email_fields['success'] = workflow.success + email_fields['dateComplete'] = workflow.complete + email_fields['duration'] = workflow.duration + email_fields['exitStatus'] = workflow.exitStatus + email_fields['errorMessage'] = (workflow.errorMessage ?: 'None') + email_fields['errorReport'] = (workflow.errorReport ?: 'None') + email_fields['commandLine'] = workflow.commandLine + email_fields['projectDir'] = workflow.projectDir + email_fields['summary'] = summary << misc_fields + + // On success try attach the multiqc report + def mqc_report = attachMultiqcReport(multiqc_report) + + // Check if we are only sending emails on failure + def email_address = email + if (!email && email_on_fail && !workflow.success) { + email_address = email_on_fail + } + + // Render the TXT template + def engine = new groovy.text.GStringTemplateEngine() + def tf = new File("${workflow.projectDir}/assets/email_template.txt") + def txt_template = engine.createTemplate(tf).make(email_fields) + def email_txt = txt_template.toString() + + // Render the HTML template + def hf = new File("${workflow.projectDir}/assets/email_template.html") + def html_template = engine.createTemplate(hf).make(email_fields) + def email_html = html_template.toString() + + // Render the sendmail template + def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit + def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "${workflow.projectDir}", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] + def sf = new File("${workflow.projectDir}/assets/sendmail_template.txt") + def sendmail_template = engine.createTemplate(sf).make(smail_fields) + def sendmail_html = sendmail_template.toString() + + // Send the HTML e-mail + Map colors = logColours(monochrome_logs) + if (email_address) { + try { + if (plaintext_email) { throw GroovyException('Send plaintext e-mail, not HTML') } + // Try to send HTML e-mail using sendmail + def sendmail_tf = new File(workflow.launchDir.toString(), ".sendmail_tmp.html") + sendmail_tf.withWriter { w -> w << sendmail_html } + [ 'sendmail', '-t' ].execute() << sendmail_html + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (sendmail)-" + } catch (all) { + // Catch failures and try with plaintext + def mail_cmd = [ 'mail', '-s', subject, '--content-type=text/html', email_address ] + mail_cmd.execute() << email_html + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Sent summary e-mail to $email_address (mail)-" + } + } + + // Write summary e-mail HTML to a file + def output_hf = new File(workflow.launchDir.toString(), ".pipeline_report.html") + output_hf.withWriter { w -> w << email_html } + FilesEx.copyTo(output_hf.toPath(), "${outdir}/pipeline_info/pipeline_report.html"); + output_hf.delete() + + // Write summary e-mail TXT to a file + def output_tf = new File(workflow.launchDir.toString(), ".pipeline_report.txt") + output_tf.withWriter { w -> w << email_txt } + FilesEx.copyTo(output_tf.toPath(), "${outdir}/pipeline_info/pipeline_report.txt"); + output_tf.delete() +} + +// +// Print pipeline summary on completion +// +def completionSummary(monochrome_logs=true) { + Map colors = logColours(monochrome_logs) + if (workflow.success) { + if (workflow.stats.ignoredCount == 0) { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.green} Pipeline completed successfully${colors.reset}-" + } else { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.yellow} Pipeline completed successfully, but with errored process(es) ${colors.reset}-" + } + } else { + log.info "-${colors.purple}[$workflow.manifest.name]${colors.red} Pipeline completed with errors${colors.reset}-" + } +} + +// +// Construct and send a notification to a web server as JSON e.g. Microsoft Teams and Slack +// +def imNotification(summary_params, hook_url) { + def summary = [:] + for (group in summary_params.keySet()) { + summary << summary_params[group] + } + + def misc_fields = [:] + misc_fields['start'] = workflow.start + misc_fields['complete'] = workflow.complete + misc_fields['scriptfile'] = workflow.scriptFile + misc_fields['scriptid'] = workflow.scriptId + if (workflow.repository) misc_fields['repository'] = workflow.repository + if (workflow.commitId) misc_fields['commitid'] = workflow.commitId + if (workflow.revision) misc_fields['revision'] = workflow.revision + misc_fields['nxf_version'] = workflow.nextflow.version + misc_fields['nxf_build'] = workflow.nextflow.build + misc_fields['nxf_timestamp'] = workflow.nextflow.timestamp + + def msg_fields = [:] + msg_fields['version'] = getWorkflowVersion() + msg_fields['runName'] = workflow.runName + msg_fields['success'] = workflow.success + msg_fields['dateComplete'] = workflow.complete + msg_fields['duration'] = workflow.duration + msg_fields['exitStatus'] = workflow.exitStatus + msg_fields['errorMessage'] = (workflow.errorMessage ?: 'None') + msg_fields['errorReport'] = (workflow.errorReport ?: 'None') + msg_fields['commandLine'] = workflow.commandLine.replaceFirst(/ +--hook_url +[^ ]+/, "") + msg_fields['projectDir'] = workflow.projectDir + msg_fields['summary'] = summary << misc_fields + + // Render the JSON template + def engine = new groovy.text.GStringTemplateEngine() + // Different JSON depending on the service provider + // Defaults to "Adaptive Cards" (https://adaptivecards.io), except Slack which has its own format + def json_path = hook_url.contains("hooks.slack.com") ? "slackreport.json" : "adaptivecard.json" + def hf = new File("${workflow.projectDir}/assets/${json_path}") + def json_template = engine.createTemplate(hf).make(msg_fields) + def json_message = json_template.toString() + + // POST + def post = new URL(hook_url).openConnection(); + post.setRequestMethod("POST") + post.setDoOutput(true) + post.setRequestProperty("Content-Type", "application/json") + post.getOutputStream().write(json_message.getBytes("UTF-8")); + def postRC = post.getResponseCode(); + if (! postRC.equals(200)) { + log.warn(post.getErrorStream().getText()); + } +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/meta.yml b/subworkflows/nf-core/utils_nfcore_pipeline/meta.yml new file mode 100644 index 00000000..d08d2434 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/meta.yml @@ -0,0 +1,24 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NFCORE_PIPELINE" +description: Subworkflow with utility functions specific to the nf-core pipeline template +keywords: + - utility + - pipeline + - initialise + - version +components: [] +input: + - nextflow_cli_args: + type: list + description: | + Nextflow CLI positional arguments +output: + - success: + type: boolean + description: | + Dummy output to indicate success +authors: + - "@adamrtalbot" +maintainers: + - "@adamrtalbot" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test new file mode 100644 index 00000000..1dc317f8 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test @@ -0,0 +1,134 @@ + +nextflow_function { + + name "Test Functions" + script "../main.nf" + config "subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "utils_nfcore_pipeline" + tag "subworkflows/utils_nfcore_pipeline" + + test("Test Function checkConfigProvided") { + + function "checkConfigProvided" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function checkProfileProvided") { + + function "checkProfileProvided" + + when { + function { + """ + input[0] = [] + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function workflowCitation") { + + function "workflowCitation" + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function nfCoreLogo") { + + function "nfCoreLogo" + + when { + function { + """ + input[0] = false + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function dashedLine") { + + function "dashedLine" + + when { + function { + """ + input[0] = false + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function without logColours") { + + function "logColours" + + when { + function { + """ + input[0] = true + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } + + test("Test Function with logColours") { + function "logColours" + + when { + function { + """ + input[0] = false + """ + } + } + + then { + assertAll( + { assert function.success }, + { assert snapshot(function.result).match() } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap new file mode 100644 index 00000000..10f948e6 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap @@ -0,0 +1,138 @@ +{ + "Test Function checkProfileProvided": { + "content": null, + "timestamp": "2024-02-09T15:43:55.145717" + }, + "Test Function checkConfigProvided": { + "content": [ + true + ], + "timestamp": "2024-01-19T11:34:13.548431224" + }, + "Test Function nfCoreLogo": { + "content": [ + "\n\n-\u001b[2m----------------------------------------------------\u001b[0m-\n \u001b[0;32m,--.\u001b[0;30m/\u001b[0;32m,-.\u001b[0m\n\u001b[0;34m ___ __ __ __ ___ \u001b[0;32m/,-._.--~'\u001b[0m\n\u001b[0;34m |\\ | |__ __ / ` / \\ |__) |__ \u001b[0;33m} {\u001b[0m\n\u001b[0;34m | \\| | \\__, \\__/ | \\ |___ \u001b[0;32m\\`-._,-`-,\u001b[0m\n \u001b[0;32m`._,._,'\u001b[0m\n\u001b[0;35m nextflow_workflow v9.9.9\u001b[0m\n-\u001b[2m----------------------------------------------------\u001b[0m-\n" + ], + "timestamp": "2024-01-19T11:34:38.840454873" + }, + "Test Function workflowCitation": { + "content": [ + "If you use nextflow_workflow for your analysis please cite:\n\n* The pipeline\n https://doi.org/10.5281/zenodo.5070524\n\n* The nf-core framework\n https://doi.org/10.1038/s41587-020-0439-x\n\n* Software dependencies\n https://github.com/nextflow_workflow/blob/master/CITATIONS.md" + ], + "timestamp": "2024-01-19T11:34:22.24352016" + }, + "Test Function without logColours": { + "content": [ + { + "reset": "", + "bold": "", + "dim": "", + "underlined": "", + "blink": "", + "reverse": "", + "hidden": "", + "black": "", + "red": "", + "green": "", + "yellow": "", + "blue": "", + "purple": "", + "cyan": "", + "white": "", + "bblack": "", + "bred": "", + "bgreen": "", + "byellow": "", + "bblue": "", + "bpurple": "", + "bcyan": "", + "bwhite": "", + "ublack": "", + "ured": "", + "ugreen": "", + "uyellow": "", + "ublue": "", + "upurple": "", + "ucyan": "", + "uwhite": "", + "iblack": "", + "ired": "", + "igreen": "", + "iyellow": "", + "iblue": "", + "ipurple": "", + "icyan": "", + "iwhite": "", + "biblack": "", + "bired": "", + "bigreen": "", + "biyellow": "", + "biblue": "", + "bipurple": "", + "bicyan": "", + "biwhite": "" + } + ], + "timestamp": "2024-01-19T11:35:04.418416984" + }, + "Test Function dashedLine": { + "content": [ + "-\u001b[2m----------------------------------------------------\u001b[0m-" + ], + "timestamp": "2024-01-19T11:34:55.420000755" + }, + "Test Function with logColours": { + "content": [ + { + "reset": "\u001b[0m", + "bold": "\u001b[1m", + "dim": "\u001b[2m", + "underlined": "\u001b[4m", + "blink": "\u001b[5m", + "reverse": "\u001b[7m", + "hidden": "\u001b[8m", + "black": "\u001b[0;30m", + "red": "\u001b[0;31m", + "green": "\u001b[0;32m", + "yellow": "\u001b[0;33m", + "blue": "\u001b[0;34m", + "purple": "\u001b[0;35m", + "cyan": "\u001b[0;36m", + "white": "\u001b[0;37m", + "bblack": "\u001b[1;30m", + "bred": "\u001b[1;31m", + "bgreen": "\u001b[1;32m", + "byellow": "\u001b[1;33m", + "bblue": "\u001b[1;34m", + "bpurple": "\u001b[1;35m", + "bcyan": "\u001b[1;36m", + "bwhite": "\u001b[1;37m", + "ublack": "\u001b[4;30m", + "ured": "\u001b[4;31m", + "ugreen": "\u001b[4;32m", + "uyellow": "\u001b[4;33m", + "ublue": "\u001b[4;34m", + "upurple": "\u001b[4;35m", + "ucyan": "\u001b[4;36m", + "uwhite": "\u001b[4;37m", + "iblack": "\u001b[0;90m", + "ired": "\u001b[0;91m", + "igreen": "\u001b[0;92m", + "iyellow": "\u001b[0;93m", + "iblue": "\u001b[0;94m", + "ipurple": "\u001b[0;95m", + "icyan": "\u001b[0;96m", + "iwhite": "\u001b[0;97m", + "biblack": "\u001b[1;90m", + "bired": "\u001b[1;91m", + "bigreen": "\u001b[1;92m", + "biyellow": "\u001b[1;93m", + "biblue": "\u001b[1;94m", + "bipurple": "\u001b[1;95m", + "bicyan": "\u001b[1;96m", + "biwhite": "\u001b[1;97m" + } + ], + "timestamp": "2024-01-19T11:35:13.436366565" + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test new file mode 100644 index 00000000..8940d32d --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test @@ -0,0 +1,29 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NFCORE_PIPELINE" + script "../main.nf" + config "subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config" + workflow "UTILS_NFCORE_PIPELINE" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "utils_nfcore_pipeline" + tag "subworkflows/utils_nfcore_pipeline" + + test("Should run without failures") { + + when { + workflow { + """ + input[0] = [] + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert snapshot(workflow.out).match() } + ) + } + } +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap new file mode 100644 index 00000000..d07ce54c --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap @@ -0,0 +1,15 @@ +{ + "Should run without failures": { + "content": [ + { + "0": [ + true + ], + "valid_config": [ + true + ] + } + ], + "timestamp": "2024-01-19T11:35:22.538940073" + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config b/subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config new file mode 100644 index 00000000..d0a926bf --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/nextflow.config @@ -0,0 +1,9 @@ +manifest { + name = 'nextflow_workflow' + author = """nf-core""" + homePage = 'https://127.0.0.1' + description = """Dummy pipeline""" + nextflowVersion = '!>=23.04.0' + version = '9.9.9' + doi = 'https://doi.org/10.5281/zenodo.5070524' +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml b/subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml new file mode 100644 index 00000000..ac8523c9 --- /dev/null +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/tags.yml @@ -0,0 +1,2 @@ +subworkflows/utils_nfcore_pipeline: + - subworkflows/nf-core/utils_nfcore_pipeline/** diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/main.nf b/subworkflows/nf-core/utils_nfvalidation_plugin/main.nf new file mode 100644 index 00000000..2585b65d --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/main.nf @@ -0,0 +1,62 @@ +// +// Subworkflow that uses the nf-validation plugin to render help text and parameter summary +// + +/* +======================================================================================== + IMPORT NF-VALIDATION PLUGIN +======================================================================================== +*/ + +include { paramsHelp } from 'plugin/nf-validation' +include { paramsSummaryLog } from 'plugin/nf-validation' +include { validateParameters } from 'plugin/nf-validation' + +/* +======================================================================================== + SUBWORKFLOW DEFINITION +======================================================================================== +*/ + +workflow UTILS_NFVALIDATION_PLUGIN { + + take: + print_help // boolean: print help + workflow_command // string: default commmand used to run pipeline + pre_help_text // string: string to be printed before help text and summary log + post_help_text // string: string to be printed after help text and summary log + validate_params // boolean: validate parameters + schema_filename // path: JSON schema file, null to use default value + + main: + + log.debug "Using schema file: ${schema_filename}" + + // Default values for strings + pre_help_text = pre_help_text ?: '' + post_help_text = post_help_text ?: '' + workflow_command = workflow_command ?: '' + + // + // Print help message if needed + // + if (print_help) { + log.info pre_help_text + paramsHelp(workflow_command, parameters_schema: schema_filename) + post_help_text + System.exit(0) + } + + // + // Print parameter summary to stdout + // + log.info pre_help_text + paramsSummaryLog(workflow, parameters_schema: schema_filename) + post_help_text + + // + // Validate parameters relative to the parameter JSON schema + // + if (validate_params){ + validateParameters(parameters_schema: schema_filename) + } + + emit: + dummy_emit = true +} diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml b/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml new file mode 100644 index 00000000..3d4a6b04 --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/meta.yml @@ -0,0 +1,44 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json +name: "UTILS_NFVALIDATION_PLUGIN" +description: Use nf-validation to initiate and validate a pipeline +keywords: + - utility + - pipeline + - initialise + - validation +components: [] +input: + - print_help: + type: boolean + description: | + Print help message and exit + - workflow_command: + type: string + description: | + The command to run the workflow e.g. "nextflow run main.nf" + - pre_help_text: + type: string + description: | + Text to print before the help message + - post_help_text: + type: string + description: | + Text to print after the help message + - validate_params: + type: boolean + description: | + Validate the parameters and error if invalid. + - schema_filename: + type: string + description: | + The filename of the schema to validate against. +output: + - dummy_emit: + type: boolean + description: | + Dummy emit to make nf-core subworkflows lint happy +authors: + - "@adamrtalbot" +maintainers: + - "@adamrtalbot" + - "@maxulysse" diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test new file mode 100644 index 00000000..517ee54e --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test @@ -0,0 +1,200 @@ +nextflow_workflow { + + name "Test Workflow UTILS_NFVALIDATION_PLUGIN" + script "../main.nf" + workflow "UTILS_NFVALIDATION_PLUGIN" + tag "subworkflows" + tag "subworkflows_nfcore" + tag "plugin/nf-validation" + tag "'plugin/nf-validation'" + tag "utils_nfvalidation_plugin" + tag "subworkflows/utils_nfvalidation_plugin" + + test("Should run nothing") { + + when { + + params { + monochrome_logs = true + test_data = '' + } + + workflow { + """ + help = false + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success } + ) + } + } + + test("Should run help") { + + + when { + + params { + monochrome_logs = true + test_data = '' + } + workflow { + """ + help = true + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.exitStatus == 0 }, + { assert workflow.stdout.any { it.contains('Input/output options') } }, + { assert workflow.stdout.any { it.contains('--outdir') } } + ) + } + } + + test("Should run help with command") { + + when { + + params { + monochrome_logs = true + test_data = '' + } + workflow { + """ + help = true + workflow_command = "nextflow run noorg/doesntexist" + pre_help_text = null + post_help_text = null + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.exitStatus == 0 }, + { assert workflow.stdout.any { it.contains('nextflow run noorg/doesntexist') } }, + { assert workflow.stdout.any { it.contains('Input/output options') } }, + { assert workflow.stdout.any { it.contains('--outdir') } } + ) + } + } + + test("Should run help with extra text") { + + + when { + + params { + monochrome_logs = true + test_data = '' + } + workflow { + """ + help = true + workflow_command = "nextflow run noorg/doesntexist" + pre_help_text = "pre-help-text" + post_help_text = "post-help-text" + validate_params = false + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.success }, + { assert workflow.exitStatus == 0 }, + { assert workflow.stdout.any { it.contains('pre-help-text') } }, + { assert workflow.stdout.any { it.contains('nextflow run noorg/doesntexist') } }, + { assert workflow.stdout.any { it.contains('Input/output options') } }, + { assert workflow.stdout.any { it.contains('--outdir') } }, + { assert workflow.stdout.any { it.contains('post-help-text') } } + ) + } + } + + test("Should validate params") { + + when { + + params { + monochrome_logs = true + test_data = '' + outdir = 1 + } + workflow { + """ + help = false + workflow_command = null + pre_help_text = null + post_help_text = null + validate_params = true + schema_filename = "$moduleTestDir/nextflow_schema.json" + + input[0] = help + input[1] = workflow_command + input[2] = pre_help_text + input[3] = post_help_text + input[4] = validate_params + input[5] = schema_filename + """ + } + } + + then { + assertAll( + { assert workflow.failed }, + { assert workflow.stdout.any { it.contains('ERROR ~ ERROR: Validation of pipeline parameters failed!') } } + ) + } + } +} \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json new file mode 100644 index 00000000..7626c1c9 --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/nextflow_schema.json @@ -0,0 +1,96 @@ +{ + "$schema": "http://json-schema.org/draft-07/schema", + "$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json", + "title": ". pipeline parameters", + "description": "", + "type": "object", + "definitions": { + "input_output_options": { + "title": "Input/output options", + "type": "object", + "fa_icon": "fas fa-terminal", + "description": "Define where the pipeline should find input data and save output data.", + "required": ["outdir"], + "properties": { + "validate_params": { + "type": "boolean", + "description": "Validate parameters?", + "default": true, + "hidden": true + }, + "outdir": { + "type": "string", + "format": "directory-path", + "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.", + "fa_icon": "fas fa-folder-open" + }, + "test_data_base": { + "type": "string", + "default": "https://raw.githubusercontent.com/nf-core/test-datasets/modules", + "description": "Base for test data directory", + "hidden": true + }, + "test_data": { + "type": "string", + "description": "Fake test data param", + "hidden": true + } + } + }, + "generic_options": { + "title": "Generic options", + "type": "object", + "fa_icon": "fas fa-file-import", + "description": "Less common options for the pipeline, typically set in a config file.", + "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.", + "properties": { + "help": { + "type": "boolean", + "description": "Display help text.", + "fa_icon": "fas fa-question-circle", + "hidden": true + }, + "version": { + "type": "boolean", + "description": "Display version and exit.", + "fa_icon": "fas fa-question-circle", + "hidden": true + }, + "logo": { + "type": "boolean", + "default": true, + "description": "Display nf-core logo in console output.", + "fa_icon": "fas fa-image", + "hidden": true + }, + "singularity_pull_docker_container": { + "type": "boolean", + "description": "Pull Singularity container from Docker?", + "hidden": true + }, + "publish_dir_mode": { + "type": "string", + "default": "copy", + "description": "Method used to save pipeline results to output directory.", + "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.", + "fa_icon": "fas fa-copy", + "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"], + "hidden": true + }, + "monochrome_logs": { + "type": "boolean", + "description": "Use monochrome_logs", + "hidden": true + } + } + } + }, + "allOf": [ + { + "$ref": "#/definitions/input_output_options" + }, + { + "$ref": "#/definitions/generic_options" + } + ] +} diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml new file mode 100644 index 00000000..60b1cfff --- /dev/null +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/tags.yml @@ -0,0 +1,2 @@ +subworkflows/utils_nfvalidation_plugin: + - subworkflows/nf-core/utils_nfvalidation_plugin/** diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 115b6b48..40e0dfdb 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -1,54 +1,15 @@ /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - PRINT PARAMS SUMMARY + IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' - -def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) -def citation = '\n' + WorkflowMain.citation(workflow) + '\n' -def summary_params = paramsSummaryMap(workflow) - -// Print parameter summary log to screen -log.info logo + paramsSummaryLog(workflow) + citation - -WorkflowScrnaseq.initialise(params, log) - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - CONFIG FILES -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) -ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath( params.multiqc_config, checkIfExists: true ) : Channel.empty() -ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath( params.multiqc_logo, checkIfExists: true ) : Channel.empty() -ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - IMPORT LOCAL MODULES/SUBWORKFLOWS -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -// -// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules -// -include { INPUT_CHECK } from '../subworkflows/local/input_check' - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - IMPORT NF-CORE MODULES/SUBWORKFLOWS -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -// -// MODULE: Installed directly from nf-core/modules -// -include { FASTQC } from '../modules/nf-core/fastqc/main' -include { MULTIQC } from '../modules/nf-core/multiqc/main' -include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' +include { FASTQC } from '../modules/nf-core/fastqc/main' +include { MULTIQC } from '../modules/nf-core/multiqc/main' +include { paramsSummaryMap } from 'plugin/nf-validation' +include { paramsSummaryMultiqc } from '../subworkflows/nf-core/utils_nfcore_pipeline' +include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline' +include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_scrnaseq_pipeline' /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -56,50 +17,45 @@ include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoft ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -// Info required for completion email and summary -def multiqc_report = [] - workflow SCRNASEQ { - ch_versions = Channel.empty() + take: + ch_samplesheet // channel: samplesheet read in from --input - // - // SUBWORKFLOW: Read in samplesheet, validate and stage input files - // - INPUT_CHECK ( - file(params.input) - ) - ch_versions = ch_versions.mix(INPUT_CHECK.out.versions) - // TODO: OPTIONAL, you can use nf-validation plugin to create an input channel from the samplesheet with Channel.fromSamplesheet("input") - // See the documentation https://nextflow-io.github.io/nf-validation/samplesheets/fromSamplesheet/ - // ! There is currently no tooling to help you write a sample sheet schema + main: + + ch_versions = Channel.empty() + ch_multiqc_files = Channel.empty() // // MODULE: Run FastQC // FASTQC ( - INPUT_CHECK.out.reads + ch_samplesheet ) + ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}) ch_versions = ch_versions.mix(FASTQC.out.versions.first()) - CUSTOM_DUMPSOFTWAREVERSIONS ( - ch_versions.unique().collectFile(name: 'collated_versions.yml') - ) + // + // Collate and save software versions + // + softwareVersionsToYAML(ch_versions) + .collectFile(storeDir: "${params.outdir}/pipeline_info", name: 'nf_core_pipeline_software_mqc_versions.yml', sort: true, newLine: true) + .set { ch_collated_versions } // // MODULE: MultiQC // - workflow_summary = WorkflowScrnaseq.paramsSummaryMultiqc(workflow, summary_params) - ch_workflow_summary = Channel.value(workflow_summary) - - methods_description = WorkflowScrnaseq.methodsDescriptionText(workflow, ch_multiqc_custom_methods_description, params) - ch_methods_description = Channel.value(methods_description) - - ch_multiqc_files = Channel.empty() - ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect()) - ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([])) + ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) + ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multiqc_config, checkIfExists: true) : Channel.empty() + ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath(params.multiqc_logo, checkIfExists: true) : Channel.empty() + summary_params = paramsSummaryMap(workflow, parameters_schema: "nextflow_schema.json") + ch_workflow_summary = Channel.value(paramsSummaryMultiqc(summary_params)) + ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) + ch_methods_description = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description)) + ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) + ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions) + ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false)) MULTIQC ( ch_multiqc_files.collect(), @@ -107,31 +63,10 @@ workflow SCRNASEQ { ch_multiqc_custom_config.toList(), ch_multiqc_logo.toList() ) - multiqc_report = MULTIQC.out.report.toList() -} - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - COMPLETION EMAIL AND SUMMARY -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -workflow.onComplete { - if (params.email || params.email_on_fail) { - NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) - } - NfcoreTemplate.dump_parameters(workflow, params) - NfcoreTemplate.summary(workflow, params, log) - if (params.hook_url) { - NfcoreTemplate.IM_notification(workflow, params, summary_params, projectDir, log) - } -} -workflow.onError { - if (workflow.errorReport.contains("Process requirement exceeds available memory")) { - println("🛑 Default resources exceed availability 🛑 ") - println("💡 See here on how to configure pipeline: https://nf-co.re/docs/usage/configuration#tuning-workflow-resources 💡") - } + emit: + multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html + versions = ch_versions // channel: [ path(versions.yml) ] } /* From bf276856b4159b0da100f33f1c1cb5f8a792e0a6 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Fri, 23 Feb 2024 11:32:52 -0800 Subject: [PATCH 16/49] harmonizing with PR while that's in progress --- modules/nf-core/kallistobustools/count/main.nf | 4 ++-- modules/nf-core/kallistobustools/count/meta.yml | 4 ++-- .../nf-core/kallistobustools/ref/environment.yml | 3 ++- modules/nf-core/kallistobustools/ref/main.nf | 8 ++++---- modules/nf-core/kallistobustools/ref/meta.yml | 14 +++++++------- 5 files changed, 17 insertions(+), 16 deletions(-) diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index 9e860241..ce5b5365 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -27,7 +27,7 @@ process KALLISTOBUSTOOLS_COUNT { def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" def cdna = t1c ? "-c1 $t1c" : '' - def unprocessed = t2c ? "-c2 $t2c" : '' + def intron = t2c ? "-c2 $t2c" : '' def memory = task.memory.toGiga() - 1 """ kb \\ @@ -36,7 +36,7 @@ process KALLISTOBUSTOOLS_COUNT { -i $index \\ -g $t2g \\ $cdna \\ - $unprocessed \\ + $intron \\ -x $technology \\ $args \\ -o ${prefix}.count \\ diff --git a/modules/nf-core/kallistobustools/count/meta.yml b/modules/nf-core/kallistobustools/count/meta.yml index c8763343..4a5d4b88 100644 --- a/modules/nf-core/kallistobustools/count/meta.yml +++ b/modules/nf-core/kallistobustools/count/meta.yml @@ -38,8 +38,8 @@ input: pattern: "*.{cdna_t2c.txt}" - t2c: type: file - description: kb ref's c2 unprocessed_t2c file - pattern: "*.{unprocessed_t2c.txt}" + description: kb ref's c2 intron_t2c file + pattern: "*.{intron_t2c.txt}" - workflow_mode: type: string description: String value defining workflow to use, can be one of "standard", "nac", "lamanno" (obsolete) diff --git a/modules/nf-core/kallistobustools/ref/environment.yml b/modules/nf-core/kallistobustools/ref/environment.yml index 62942e01..82aafedb 100644 --- a/modules/nf-core/kallistobustools/ref/environment.yml +++ b/modules/nf-core/kallistobustools/ref/environment.yml @@ -5,4 +5,5 @@ channels: - defaults dependencies: - bioconda::kb-python=0.28.2 - - conda-forge::requests>=2.23.0 \ No newline at end of file + - conda-forge::requests>=2.23.0 + \ No newline at end of file diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf index 989f86f3..759e8663 100644 --- a/modules/nf-core/kallistobustools/ref/main.nf +++ b/modules/nf-core/kallistobustools/ref/main.nf @@ -17,9 +17,9 @@ process KALLISTOBUSTOOLS_REF { path "kb_ref_out.idx" , emit: index path "t2g.txt" , emit: t2g path "cdna.fa" , emit: cdna - path "unprocessed.fa" , optional:true, emit: unprocessed + path "intron.fa" , optional:true, emit: intron path "cdna_t2c.txt" , optional:true, emit: cdna_t2c - path "unprocessed_t2c.txt" , optional:true, emit: unprocessed_t2c + path "intron_t2c.txt" , optional:true, emit: intron_t2c when: task.ext.when == null || task.ext.when @@ -49,9 +49,9 @@ process KALLISTOBUSTOOLS_REF { -i kb_ref_out.idx \\ -g t2g.txt \\ -f1 cdna.fa \\ - -f2 unprocessed.fa \\ + -f2 intron.fa \\ -c1 cdna_t2c.txt \\ - -c2 unprocessed_t2c.txt \\ + -c2 intron_t2c.txt \\ --workflow $workflow_mode \\ $fasta \\ $gtf diff --git a/modules/nf-core/kallistobustools/ref/meta.yml b/modules/nf-core/kallistobustools/ref/meta.yml index 1ca31c57..0c3f78a4 100644 --- a/modules/nf-core/kallistobustools/ref/meta.yml +++ b/modules/nf-core/kallistobustools/ref/meta.yml @@ -45,19 +45,19 @@ output: type: file description: cDNA fasta file pattern: "*cdna.{fa}" - - unprocessed: + - intron: type: file - description: Unprocessed fasta file - pattern: "*unprocessed.{fa}" + description: Intron fasta file + pattern: "*intron.{fa}" - cdna_t2c: type: file description: cDNA transcript to capture file pattern: "*cdna_t2c.{txt}" - - unprocessed_t2c: + - intron_t2c: type: file - description: Unprocessed transcript to capture file - pattern: "*unprocessed_t2c.{txt}" + description: Intron transcript to capture file + pattern: "*intron_t2c.{txt}" authors: - - "@flowuenne" + - "@flowuenne" maintainers: - "@flowuenne" From ac7e7cdfe24cf39e9b432d21e1a077e45da39684 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Fri, 23 Feb 2024 13:00:01 -0800 Subject: [PATCH 17/49] Update nextflow_schema.json --- nextflow_schema.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 10087c2c..2d204477 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -220,9 +220,9 @@ "kb_workflow": { "type": "string", "default": "standard", - "description": "Type of workflow. Use `lamanno` for RNA velocity based on La Manno et al. 2018 logic. Use `nucleus` for RNA velocity on single-nucleus RNA-seq reads. Use `kite` for feature barcoding. Use `kite: 10xFB` for 10x Genomics Feature Barcoding technology. (default: standard)", + "description": "Type of workflow. Use `nac` for an index type that can quantify nascent and mature RNA. Use `lamanno` for RNA velocity based on La Manno et al. 2018 logic. (default: standard)", "fa_icon": "fas fa-rainbow", - "enum": ["standard", "lamanno", "nucleus", "kite", "kite: 10xFB"] + "enum": ["standard", "lamanno", "nac"] } } }, From 8c4b8723b298a8f02c291e2f011f7e39660a0d11 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Fri, 23 Feb 2024 14:35:01 -0800 Subject: [PATCH 18/49] Update main.nf --- modules/nf-core/kallistobustools/count/main.nf | 2 ++ 1 file changed, 2 insertions(+) diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index ce5b5365..4679fe97 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -14,6 +14,7 @@ process KALLISTOBUSTOOLS_COUNT { path t1c path t2c val technology + val workflow_mode output: tuple val(meta), path ("*.count"), emit: count @@ -38,6 +39,7 @@ process KALLISTOBUSTOOLS_COUNT { $cdna \\ $intron \\ -x $technology \\ + --workflow $workflow_mode \\ $args \\ -o ${prefix}.count \\ -m ${memory}G \\ From 8db2f9553da65c4814523a1bd548a41dc50b72f2 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Fri, 23 Feb 2024 16:03:08 -0800 Subject: [PATCH 19/49] Update kallisto_bustools.nf --- subworkflows/local/kallisto_bustools.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 7fdaf8ef..8b16dc56 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -34,7 +34,7 @@ workflow KALLISTO_BUSTOOLS { kallisto_index = KALLISTOBUSTOOLS_REF.out.index.collect() ch_versions = ch_versions.mix(KALLISTOBUSTOOLS_REF.out.versions) t1c = KALLISTOBUSTOOLS_REF.out.cdna_t2c.ifEmpty{ [] } - t2c = KALLISTOBUSTOOLS_REF.out.unprocessed_t2c.ifEmpty{ [] } + t2c = KALLISTOBUSTOOLS_REF.out.intron_t2c.ifEmpty{ [] } } /* From a1fdcda8a13ade6c5218cd11f9068ab609b45746 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Fri, 23 Feb 2024 16:09:08 -0800 Subject: [PATCH 20/49] Update kallisto_bustools.nf --- subworkflows/local/kallisto_bustools.nf | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/subworkflows/local/kallisto_bustools.nf b/subworkflows/local/kallisto_bustools.nf index 8b16dc56..b6549094 100644 --- a/subworkflows/local/kallisto_bustools.nf +++ b/subworkflows/local/kallisto_bustools.nf @@ -46,7 +46,8 @@ workflow KALLISTO_BUSTOOLS { txp2gene, t1c, t2c, - protocol + protocol, + kb_workflow ) ch_versions = ch_versions.mix(KALLISTOBUSTOOLS_COUNT.out.versions) From 2aca75b5df3c90dc3284995b2c1713b9c8ec7747 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 11:39:50 -0800 Subject: [PATCH 21/49] docker container update --- modules/nf-core/kallistobustools/count/main.nf | 4 ++-- modules/nf-core/kallistobustools/count/meta.yml | 2 +- modules/nf-core/kallistobustools/ref/environment.yml | 1 - modules/nf-core/kallistobustools/ref/main.nf | 4 ++-- modules/nf-core/kallistobustools/ref/meta.yml | 2 +- 5 files changed, 6 insertions(+), 7 deletions(-) diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index 4679fe97..67ad5812 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -4,8 +4,8 @@ process KALLISTOBUSTOOLS_COUNT { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_0' : - 'biocontainers/kb-python:0.28.2--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_2' : + 'biocontainers/kb-python:0.28.2--pyhdfd78af_2' }" input: tuple val(meta), path(reads) diff --git a/modules/nf-core/kallistobustools/count/meta.yml b/modules/nf-core/kallistobustools/count/meta.yml index 4a5d4b88..55d5dc6c 100644 --- a/modules/nf-core/kallistobustools/count/meta.yml +++ b/modules/nf-core/kallistobustools/count/meta.yml @@ -12,7 +12,7 @@ tools: homepage: https://www.kallistobus.tools/ documentation: https://kb-python.readthedocs.io/en/latest/index.html tool_dev_url: https://github.com/pachterlab/kb_python - licence: MIT License + licence: ["MIT"] input: - meta: type: map diff --git a/modules/nf-core/kallistobustools/ref/environment.yml b/modules/nf-core/kallistobustools/ref/environment.yml index 82aafedb..6ae07a8c 100644 --- a/modules/nf-core/kallistobustools/ref/environment.yml +++ b/modules/nf-core/kallistobustools/ref/environment.yml @@ -6,4 +6,3 @@ channels: dependencies: - bioconda::kb-python=0.28.2 - conda-forge::requests>=2.23.0 - \ No newline at end of file diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf index 759e8663..702317d3 100644 --- a/modules/nf-core/kallistobustools/ref/main.nf +++ b/modules/nf-core/kallistobustools/ref/main.nf @@ -4,8 +4,8 @@ process KALLISTOBUSTOOLS_REF { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_0' : - 'biocontainers/kb-python:0.28.2--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_2' : + 'biocontainers/kb-python:0.28.2--pyhdfd78af_2' }" input: path fasta diff --git a/modules/nf-core/kallistobustools/ref/meta.yml b/modules/nf-core/kallistobustools/ref/meta.yml index 0c3f78a4..64deab9b 100644 --- a/modules/nf-core/kallistobustools/ref/meta.yml +++ b/modules/nf-core/kallistobustools/ref/meta.yml @@ -14,7 +14,7 @@ tools: documentation: https://kb-python.readthedocs.io/en/latest/index.html tool_dev_url: https://github.com/pachterlab/kb_python doi: "10.22002/D1.1876" - licence: MIT License + licence: ["MIT"] input: - fasta: type: file From 0f5609325d0a55adb6e7a3283bedba07e7912873 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 12:05:48 -0800 Subject: [PATCH 22/49] manually updated md5s this is not a real snapshot --- tests/main_pipeline_kallisto.test.snap | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tests/main_pipeline_kallisto.test.snap b/tests/main_pipeline_kallisto.test.snap index b0fb50bb..94a64ad8 100644 --- a/tests/main_pipeline_kallisto.test.snap +++ b/tests/main_pipeline_kallisto.test.snap @@ -20,15 +20,17 @@ "name": "workflow", "success": true }, - "cells_x_genes.barcodes.txt:md5,18be561873e435d4587f6b3f95a0e301", + "cells_x_genes.barcodes.txt:md5,72d78bb1c1ee7cb174520b30f695aa48", + "cells_x_genes.genes.names.txt:md5,a27831417ff4ed049d5b46012b270f4d", "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6", - "cells_x_genes.mtx:md5,37d2cd8c712f9c70463e87485bf6cd36", - "cells_x_genes.barcodes.txt:md5,488437e1f5477243697efb93366e5676", + "cells_x_genes.mtx:md5,894d60da192e3788de11fa8fc1fa711d", + "cells_x_genes.barcodes.txt:md5,a8cf7ea4b2d075296a94bf066a64b7a4", + "cells_x_genes.genes.names.txt:md5,a27831417ff4ed049d5b46012b270f4d", "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6", - "cells_x_genes.mtx:md5,af90e05b404490f6cb133ab7f62949f8", - "Sample_X_matrix.rds:md5,f0e43f69403f4b2e7704065421592ad0", - "Sample_Y_matrix.rds:md5,61809156e64dbdaf254cbc1c3456588e" + "cells_x_genes.mtx:md5,abd83de117204d0a77df3c92d00cc025", + "Sample_X_matrix.rds:md5,294781892964ed3c06f5c02124bb17b3", + "Sample_Y_matrix.rds:md5,b950e59c61ad3fdeb7293a1e5bfcd313" ], - "timestamp": "2024-01-23T12:19:47.921508953" + "timestamp": "2024-02-27T12:19:47.921508953" } } \ No newline at end of file From aae5fc5f618d1a4ccd40428d14050d838876f7fe Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 12:19:56 -0800 Subject: [PATCH 23/49] Update main_pipeline_kallisto.test.snap --- tests/main_pipeline_kallisto.test.snap | 2 -- 1 file changed, 2 deletions(-) diff --git a/tests/main_pipeline_kallisto.test.snap b/tests/main_pipeline_kallisto.test.snap index 94a64ad8..867947ec 100644 --- a/tests/main_pipeline_kallisto.test.snap +++ b/tests/main_pipeline_kallisto.test.snap @@ -21,11 +21,9 @@ "success": true }, "cells_x_genes.barcodes.txt:md5,72d78bb1c1ee7cb174520b30f695aa48", - "cells_x_genes.genes.names.txt:md5,a27831417ff4ed049d5b46012b270f4d", "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6", "cells_x_genes.mtx:md5,894d60da192e3788de11fa8fc1fa711d", "cells_x_genes.barcodes.txt:md5,a8cf7ea4b2d075296a94bf066a64b7a4", - "cells_x_genes.genes.names.txt:md5,a27831417ff4ed049d5b46012b270f4d", "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6", "cells_x_genes.mtx:md5,abd83de117204d0a77df3c92d00cc025", "Sample_X_matrix.rds:md5,294781892964ed3c06f5c02124bb17b3", From 740a5dc6254f122b94816b43706cf84cd94cf189 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 13:01:57 -0800 Subject: [PATCH 24/49] update mtx construction mtx should take in nascent/ambiguous/mature matrices. The genes.names txt contains gene names, which are typically what is desired (e.g. cellranger has names rather than IDs) --- modules/local/mtx_to_h5ad.nf | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/modules/local/mtx_to_h5ad.nf b/modules/local/mtx_to_h5ad.nf index 84d98608..043febf1 100644 --- a/modules/local/mtx_to_h5ad.nf +++ b/modules/local/mtx_to_h5ad.nf @@ -27,7 +27,7 @@ process MTX_TO_H5AD { if (params.aligner == 'kallisto') { mtx_matrix = "*count/counts_unfiltered/*.mtx" barcodes_tsv = "*count/counts_unfiltered/*.barcodes.txt" - features_tsv = "*count/counts_unfiltered/*.genes.txt" + features_tsv = "*count/counts_unfiltered/*.genes.names.txt" } else if (params.aligner == 'alevin') { mtx_matrix = "*_alevin_results/af_quant/alevin/quants_mat.mtx" barcodes_tsv = "*_alevin_results/af_quant/alevin/quants_mat_rows.txt" @@ -54,13 +54,13 @@ process MTX_TO_H5AD { else if (params.aligner == 'kallisto' && params.kb_workflow != 'standard') """ # convert file types - for input_type in spliced unspliced ; do + for input_type in nascent ambiguous mature ; do mtx_to_h5ad.py \\ --aligner ${params.aligner} \\ --sample ${meta.id} \\ - --input *count/counts_unfiltered/\${input_type}.mtx \\ - --barcode *count/counts_unfiltered/\${input_type}.barcodes.txt \\ - --feature *count/counts_unfiltered/\${input_type}.genes.txt \\ + --input *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ + --barcode *count/counts_unfiltered/cells_x_genes.\${input_type}.barcodes.txt \\ + --feature *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ --txp2gene ${txp2gene} \\ --star_index ${star_index} \\ --out ${meta.id}/${meta.id}_\${input_type}_matrix.h5ad ; From e7f59949be73f0a045d16ab266b390a9c5bab95e Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 13:22:22 -0800 Subject: [PATCH 25/49] update seurat too --- modules/local/mtx_to_seurat.nf | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/modules/local/mtx_to_seurat.nf b/modules/local/mtx_to_seurat.nf index d83575a4..04710f37 100644 --- a/modules/local/mtx_to_seurat.nf +++ b/modules/local/mtx_to_seurat.nf @@ -26,7 +26,7 @@ process MTX_TO_SEURAT { } else if (params.aligner == "kallisto") { matrix = "*count/counts_unfiltered/*.mtx" barcodes = "*count/counts_unfiltered/*.barcodes.txt" - features = "*count/counts_unfiltered/*.genes.txt" + features = "*count/counts_unfiltered/*.genes.names.txt" } else if (params.aligner == "alevin") { matrix = "*_alevin_results/af_quant/alevin/quants_mat.mtx" barcodes = "*_alevin_results/af_quant/alevin/quants_mat_rows.txt" @@ -43,11 +43,11 @@ process MTX_TO_SEURAT { if (params.aligner == 'kallisto' && params.kb_workflow != 'standard') """ # convert file types - for input_type in spliced unspliced ; do + for input_type in nascent ambiguous mature ; do mtx_to_seurat.R \\ - *count/counts_unfiltered/\${input_type}.mtx \\ - *count/counts_unfiltered/\${input_type}.barcodes.txt \\ - *count/counts_unfiltered/\${input_type}.genes.txt \\ + *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ + *count/counts_unfiltered/cells_x_genes.\${input_type}.barcodes.txt \\ + *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ ${meta.id}/${meta.id}_\${input_type}_matrix.rds \\ ${aligner} done From 25ecada467c7a43d9b6450d25523f4d06fcadff2 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 13:40:33 -0800 Subject: [PATCH 26/49] this must have gotten fixed a few kb versions ago --- modules/local/mtx_to_h5ad.nf | 2 +- modules/local/mtx_to_seurat.nf | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/local/mtx_to_h5ad.nf b/modules/local/mtx_to_h5ad.nf index 043febf1..7bde6e79 100644 --- a/modules/local/mtx_to_h5ad.nf +++ b/modules/local/mtx_to_h5ad.nf @@ -59,7 +59,7 @@ process MTX_TO_H5AD { --aligner ${params.aligner} \\ --sample ${meta.id} \\ --input *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ - --barcode *count/counts_unfiltered/cells_x_genes.\${input_type}.barcodes.txt \\ + --barcode $barcodes_tsv \\ --feature *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ --txp2gene ${txp2gene} \\ --star_index ${star_index} \\ diff --git a/modules/local/mtx_to_seurat.nf b/modules/local/mtx_to_seurat.nf index 04710f37..a9ff508f 100644 --- a/modules/local/mtx_to_seurat.nf +++ b/modules/local/mtx_to_seurat.nf @@ -46,7 +46,7 @@ process MTX_TO_SEURAT { for input_type in nascent ambiguous mature ; do mtx_to_seurat.R \\ *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ - *count/counts_unfiltered/cells_x_genes.\${input_type}.barcodes.txt \\ + $barcodes_tsv \\ *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ ${meta.id}/${meta.id}_\${input_type}_matrix.rds \\ ${aligner} From 072d187a29b1cd6c5f81bfa599b64920e0599ebb Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 13:49:26 -0800 Subject: [PATCH 27/49] ...and the R changes have to be updated in md5 --- tests/main_pipeline_kallisto.test.snap | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/main_pipeline_kallisto.test.snap b/tests/main_pipeline_kallisto.test.snap index 867947ec..00fbb2b2 100644 --- a/tests/main_pipeline_kallisto.test.snap +++ b/tests/main_pipeline_kallisto.test.snap @@ -26,8 +26,8 @@ "cells_x_genes.barcodes.txt:md5,a8cf7ea4b2d075296a94bf066a64b7a4", "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6", "cells_x_genes.mtx:md5,abd83de117204d0a77df3c92d00cc025", - "Sample_X_matrix.rds:md5,294781892964ed3c06f5c02124bb17b3", - "Sample_Y_matrix.rds:md5,b950e59c61ad3fdeb7293a1e5bfcd313" + "Sample_X_matrix.rds:md5,0938f4189b7a7fd1030abfcee798741c", + "Sample_Y_matrix.rds:md5,93c12abe283ab37c5f37e5cd3cb25302" ], "timestamp": "2024-02-27T12:19:47.921508953" } From e006cdf2255ca793b303f7072b8c34687ac70909 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 13:53:28 -0800 Subject: [PATCH 28/49] correcting var --- modules/local/mtx_to_seurat.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/local/mtx_to_seurat.nf b/modules/local/mtx_to_seurat.nf index a9ff508f..ac21e639 100644 --- a/modules/local/mtx_to_seurat.nf +++ b/modules/local/mtx_to_seurat.nf @@ -46,7 +46,7 @@ process MTX_TO_SEURAT { for input_type in nascent ambiguous mature ; do mtx_to_seurat.R \\ *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ - $barcodes_tsv \\ + $barcodes \\ *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ ${meta.id}/${meta.id}_\${input_type}_matrix.rds \\ ${aligner} From 0187f8c2c036f301005450eaa635c6640ab610e8 Mon Sep 17 00:00:00 2001 From: gennadyFauna <153561808+gennadyFauna@users.noreply.github.com> Date: Tue, 27 Feb 2024 14:16:38 -0800 Subject: [PATCH 29/49] features too --- modules/local/mtx_to_h5ad.nf | 2 +- modules/local/mtx_to_seurat.nf | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/local/mtx_to_h5ad.nf b/modules/local/mtx_to_h5ad.nf index 7bde6e79..c991b695 100644 --- a/modules/local/mtx_to_h5ad.nf +++ b/modules/local/mtx_to_h5ad.nf @@ -60,7 +60,7 @@ process MTX_TO_H5AD { --sample ${meta.id} \\ --input *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ --barcode $barcodes_tsv \\ - --feature *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ + --feature $features_tsv \\ --txp2gene ${txp2gene} \\ --star_index ${star_index} \\ --out ${meta.id}/${meta.id}_\${input_type}_matrix.h5ad ; diff --git a/modules/local/mtx_to_seurat.nf b/modules/local/mtx_to_seurat.nf index ac21e639..82ee63cd 100644 --- a/modules/local/mtx_to_seurat.nf +++ b/modules/local/mtx_to_seurat.nf @@ -47,7 +47,7 @@ process MTX_TO_SEURAT { mtx_to_seurat.R \\ *count/counts_unfiltered/cells_x_genes.\${input_type}.mtx \\ $barcodes \\ - *count/counts_unfiltered/cells_x_genes.\${input_type}.genes.names.txt \\ + $features \\ ${meta.id}/${meta.id}_\${input_type}_matrix.rds \\ ${aligner} done From a67a718482463481af6828e15b23290cf6bd6a3f Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Thu, 29 Feb 2024 16:12:47 +0000 Subject: [PATCH 30/49] Template update for nf-core/tools version 2.13.1 --- .devcontainer/devcontainer.json | 10 +---- .github/CONTRIBUTING.md | 14 ++++--- .github/PULL_REQUEST_TEMPLATE.md | 2 +- .github/workflows/awsfulltest.yml | 4 +- .github/workflows/awstest.yml | 4 +- .github/workflows/ci.yml | 2 +- .github/workflows/download_pipeline.yml | 2 +- .github/workflows/linting.yml | 2 +- .github/workflows/release-announcements.yml | 2 +- .gitpod.yml | 6 +-- README.md | 3 +- modules.json | 8 ++-- modules/nf-core/multiqc/environment.yml | 2 +- modules/nf-core/multiqc/main.nf | 4 +- .../nf-core/multiqc/tests/main.nf.test.snap | 12 +++--- .../utils_nfcore_scrnaseq_pipeline/main.nf | 10 +++-- .../tests/main.function.nf.test | 2 +- .../tests/main.function.nf.test.snap | 12 +++++- .../tests/main.workflow.nf.test | 20 ++------- .../tests/nextflow.config | 2 +- .../tests/main.function.nf.test.snap | 42 +++++++++++++++---- .../tests/main.workflow.nf.test.snap | 6 ++- .../tests/main.nf.test | 2 +- 23 files changed, 99 insertions(+), 74 deletions(-) diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json index 4ecfbfe3..b290e090 100644 --- a/.devcontainer/devcontainer.json +++ b/.devcontainer/devcontainer.json @@ -10,15 +10,7 @@ "vscode": { // Set *default* container specific settings.json values on container create. "settings": { - "python.defaultInterpreterPath": "/opt/conda/bin/python", - "python.linting.enabled": true, - "python.linting.pylintEnabled": true, - "python.formatting.autopep8Path": "/opt/conda/bin/autopep8", - "python.formatting.yapfPath": "/opt/conda/bin/yapf", - "python.linting.flake8Path": "/opt/conda/bin/flake8", - "python.linting.pycodestylePath": "/opt/conda/bin/pycodestyle", - "python.linting.pydocstylePath": "/opt/conda/bin/pydocstyle", - "python.linting.pylintPath": "/opt/conda/bin/pylint" + "python.defaultInterpreterPath": "/opt/conda/bin/python" }, // Add the IDs of extensions you want installed when the container is created. diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 597c854d..d2dc65c3 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -9,9 +9,8 @@ Please use the pre-filled template to save time. However, don't be put off by this template - other more general issues and suggestions are welcome! Contributions to the code are even more welcome ;) -:::info -If you need help using or modifying nf-core/scrnaseq then the best place to ask is on the nf-core Slack [#scrnaseq](https://nfcore.slack.com/channels/scrnaseq) channel ([join our Slack here](https://nf-co.re/join/slack)). -::: +> [!NOTE] +> If you need help using or modifying nf-core/scrnaseq then the best place to ask is on the nf-core Slack [#scrnaseq](https://nfcore.slack.com/channels/scrnaseq) channel ([join our Slack here](https://nf-co.re/join/slack)). ## Contribution workflow @@ -27,8 +26,11 @@ If you're not used to this workflow with git, you can start with some [docs from ## Tests -You can optionally test your changes by running the pipeline locally. Then it is recommended to use the `debug` profile to -receive warnings about process selectors and other debug info. Example: `nextflow run . -profile debug,test,docker --outdir `. +You have the option to test your changes locally by running the pipeline. For receiving warnings about process selectors and other `debug` information, it is recommended to use the debug profile. Execute all the tests with the following command: + +```bash +nf-test test --profile debug,test,docker --verbose +``` When you create a pull request with changes, [GitHub Actions](https://github.com/features/actions) will run automatic tests. Typically, pull-requests are only fully reviewed when these tests are passing, though of course we can help out before then. @@ -90,7 +92,7 @@ Once there, use `nf-core schema build` to add to `nextflow_schema.json`. Sensible defaults for process resource requirements (CPUs / memory / time) for a process should be defined in `conf/base.config`. These should generally be specified generic with `withLabel:` selectors so they can be shared across multiple processes/steps of the pipeline. A nf-core standard set of labels that should be followed where possible can be seen in the [nf-core pipeline template](https://github.com/nf-core/tools/blob/master/nf_core/pipeline-template/conf/base.config), which has the default process as a single core-process, and then different levels of multi-core configurations for increasingly large memory requirements defined with standardised labels. -The process resources can be passed on to the tool dynamically within the process with the `${task.cpu}` and `${task.memory}` variables in the `script:` block. +The process resources can be passed on to the tool dynamically within the process with the `${task.cpus}` and `${task.memory}` variables in the `script:` block. ### Naming schemes diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 073b2953..0767493c 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -18,7 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/scrn - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/scrnaseq/tree/master/.github/CONTRIBUTING.md) - [ ] If necessary, also make a PR on the nf-core/scrnaseq _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. - [ ] Make sure your code lints (`nf-core lint`). -- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir `). +- [ ] Ensure the test suite passes (`nf-test test main.nf.test -profile test,docker`). - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir `). - [ ] Usage Documentation in `docs/usage.md` is updated. - [ ] Output Documentation in `docs/output.md` is updated. diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index fd263945..33ee6733 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,7 +14,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: seqeralabs/action-tower-launch@922e5c8d5ac4e918107ec311d2ebbd65e5982b3d # v2 + uses: seqeralabs/action-tower-launch@v2 # TODO nf-core: You can customise AWS full pipeline tests as required # Add full size test data (but still relatively small datasets for few samples) # on the `test_full.config` test runs with only one set of parameters @@ -31,7 +31,7 @@ jobs: } profiles: test_full - - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 + - uses: actions/upload-artifact@v4 with: name: Tower debug log file path: | diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index 1f58192f..edc7b3a3 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -12,7 +12,7 @@ jobs: steps: # Launch workflow using Tower CLI tool action - name: Launch workflow via tower - uses: seqeralabs/action-tower-launch@922e5c8d5ac4e918107ec311d2ebbd65e5982b3d # v2 + uses: seqeralabs/action-tower-launch@v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} @@ -25,7 +25,7 @@ jobs: } profiles: test - - uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4 + - uses: actions/upload-artifact@v4 with: name: Tower debug log file path: | diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index e2c989ca..7b27c964 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -31,7 +31,7 @@ jobs: uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 + uses: nf-core/setup-nextflow@v1 with: version: "${{ matrix.NXF_VER }}" diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml index f823210d..08622fd5 100644 --- a/.github/workflows/download_pipeline.yml +++ b/.github/workflows/download_pipeline.yml @@ -28,7 +28,7 @@ jobs: runs-on: ubuntu-latest steps: - name: Install Nextflow - uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 + uses: nf-core/setup-nextflow@v1 - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index 748b4311..073e1876 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -35,7 +35,7 @@ jobs: uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4 - name: Install Nextflow - uses: nf-core/setup-nextflow@b9f764e8ba5c76b712ace14ecbfcef0e40ae2dd8 # v1 + uses: nf-core/setup-nextflow@v1 - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5 with: diff --git a/.github/workflows/release-announcements.yml b/.github/workflows/release-announcements.yml index c3674af2..d468aeaa 100644 --- a/.github/workflows/release-announcements.yml +++ b/.github/workflows/release-announcements.yml @@ -12,7 +12,7 @@ jobs: - name: get topics and convert to hashtags id: get_topics run: | - curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' > $GITHUB_OUTPUT + curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.full_name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' >> $GITHUB_OUTPUT - uses: rzr/fediverse-action@master with: diff --git a/.gitpod.yml b/.gitpod.yml index 363d5b1d..105a1821 100644 --- a/.gitpod.yml +++ b/.gitpod.yml @@ -10,13 +10,11 @@ tasks: vscode: extensions: # based on nf-core.nf-core-extensionpack - - codezombiech.gitignore # Language support for .gitignore files - # - cssho.vscode-svgviewer # SVG viewer - esbenp.prettier-vscode # Markdown/CommonMark linting and style checking for Visual Studio Code - - eamodio.gitlens # Quickly glimpse into whom, why, and when a line or code block was changed - EditorConfig.EditorConfig # override user/workspace settings with settings found in .editorconfig files - Gruntfuggly.todo-tree # Display TODO and FIXME in a tree view in the activity bar - mechatroner.rainbow-csv # Highlight columns in csv files in different colors - # - nextflow.nextflow # Nextflow syntax highlighting + # - nextflow.nextflow # Nextflow syntax highlighting - oderwat.indent-rainbow # Highlight indentation level - streetsidesoftware.code-spell-checker # Spelling checker for source code + - charliermarsh.ruff # Code linter Ruff diff --git a/README.md b/README.md index c80f96b1..d7e24902 100644 --- a/README.md +++ b/README.md @@ -7,12 +7,13 @@ [![GitHub Actions CI Status](https://github.com/nf-core/scrnaseq/actions/workflows/ci.yml/badge.svg)](https://github.com/nf-core/scrnaseq/actions/workflows/ci.yml) [![GitHub Actions Linting Status](https://github.com/nf-core/scrnaseq/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/scrnaseq/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/scrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) +[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com) [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/) [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/) [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/) [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/) -[![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/scrnaseq) +[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/scrnaseq) [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23scrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/scrnaseq)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core) diff --git a/modules.json b/modules.json index 59464672..01d274c2 100644 --- a/modules.json +++ b/modules.json @@ -12,7 +12,7 @@ }, "multiqc": { "branch": "master", - "git_sha": "ccacf6f5de6df3bc6d73b665c1fd2933d8bbc290", + "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a", "installed_by": ["modules"] } } @@ -21,17 +21,17 @@ "nf-core": { "utils_nextflow_pipeline": { "branch": "master", - "git_sha": "cd08c91373cd00a73255081340e4914485846ba1", + "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", "installed_by": ["subworkflows"] }, "utils_nfcore_pipeline": { "branch": "master", - "git_sha": "262b17ed2aad591039f914951659177e6c39a8d8", + "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", "installed_by": ["subworkflows"] }, "utils_nfvalidation_plugin": { "branch": "master", - "git_sha": "cd08c91373cd00a73255081340e4914485846ba1", + "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", "installed_by": ["subworkflows"] } } diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml index 2212096a..ca39fb67 100644 --- a/modules/nf-core/multiqc/environment.yml +++ b/modules/nf-core/multiqc/environment.yml @@ -4,4 +4,4 @@ channels: - bioconda - defaults dependencies: - - bioconda::multiqc=1.20 + - bioconda::multiqc=1.21 diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf index 354f4430..47ac352f 100644 --- a/modules/nf-core/multiqc/main.nf +++ b/modules/nf-core/multiqc/main.nf @@ -3,8 +3,8 @@ process MULTIQC { conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.20--pyhdfd78af_0' : - 'biocontainers/multiqc:1.20--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.21--pyhdfd78af_0' : + 'biocontainers/multiqc:1.21--pyhdfd78af_0' }" input: path multiqc_files, stageAs: "?/*" diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap index c204b488..bfebd802 100644 --- a/modules/nf-core/multiqc/tests/main.nf.test.snap +++ b/modules/nf-core/multiqc/tests/main.nf.test.snap @@ -2,14 +2,14 @@ "multiqc_versions_single": { "content": [ [ - "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], "meta": { "nf-test": "0.8.4", "nextflow": "23.10.1" }, - "timestamp": "2024-02-14T09:28:51.744211298" + "timestamp": "2024-02-29T08:48:55.657331" }, "multiqc_stub": { "content": [ @@ -17,25 +17,25 @@ "multiqc_report.html", "multiqc_data", "multiqc_plots", - "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], "meta": { "nf-test": "0.8.4", "nextflow": "23.10.1" }, - "timestamp": "2024-02-14T09:29:28.847433492" + "timestamp": "2024-02-29T08:49:49.071937" }, "multiqc_versions_config": { "content": [ [ - "versions.yml:md5,d320d4c37e349c5588e07e7a31cd4186" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], "meta": { "nf-test": "0.8.4", "nextflow": "23.10.1" }, - "timestamp": "2024-02-14T09:29:13.223621555" + "timestamp": "2024-02-29T08:49:25.457567" } } \ No newline at end of file diff --git a/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf b/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf index dc90ad90..841a0a43 100644 --- a/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf +++ b/subworkflows/local/utils_nfcore_scrnaseq_pipeline/main.nf @@ -1,5 +1,5 @@ // -// Subworkflow with functionality specific to the nf-core/pipeline pipeline +// Subworkflow with functionality specific to the nf-core/scrnaseq pipeline // /* @@ -152,7 +152,9 @@ workflow PIPELINE_COMPLETION { // def validateInputParameters() { genomeExistsError() -}// +} + +// // Validate channels from input samplesheet // def validateInputSamplesheet(input) { @@ -190,7 +192,9 @@ def genomeExistsError() { "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" error(error_string) } -}// +} + +// // Generate methods description for MultiQC // def toolCitationText() { diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test index 8ed4310c..68718e4f 100644 --- a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test @@ -51,4 +51,4 @@ nextflow_function { ) } } -} \ No newline at end of file +} diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap index db2030f8..e3f0baf4 100644 --- a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.function.nf.test.snap @@ -3,10 +3,18 @@ "content": [ "v9.9.9" ], - "timestamp": "2024-01-19T11:32:36.031083" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:02:05.308243" }, "Test Function checkCondaChannels": { "content": null, - "timestamp": "2024-01-19T11:32:50.456" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:02:12.425833" } } \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test index f7c54bc6..ca964ce8 100644 --- a/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/main.workflow.nf.test @@ -11,9 +11,6 @@ nextflow_workflow { test("Should run no inputs") { when { - params { - outdir = "tests/results" - } workflow { """ print_version = false @@ -39,9 +36,6 @@ nextflow_workflow { test("Should print version") { when { - params { - outdir = "tests/results" - } workflow { """ print_version = true @@ -68,19 +62,16 @@ nextflow_workflow { test("Should dump params") { when { - params { - outdir = "$outputDir" - } workflow { """ print_version = false dump_parameters = true - outdir = params.outdir + outdir = 'results' check_conda_channels = false input[0] = false input[1] = true - input[2] = params.outdir + input[2] = outdir input[3] = false """ } @@ -96,19 +87,16 @@ nextflow_workflow { test("Should not create params JSON if no output directory") { when { - params { - outdir = "$outputDir" - } workflow { """ print_version = false dump_parameters = true - outdir = params.outdir + outdir = null check_conda_channels = false input[0] = false input[1] = true - input[2] = null + input[2] = outdir input[3] = false """ } diff --git a/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config b/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config index 53574ffe..d0a926bf 100644 --- a/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config +++ b/subworkflows/nf-core/utils_nextflow_pipeline/tests/nextflow.config @@ -6,4 +6,4 @@ manifest { nextflowVersion = '!>=23.04.0' version = '9.9.9' doi = 'https://doi.org/10.5281/zenodo.5070524' -} \ No newline at end of file +} diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap index 10f948e6..1037232c 100644 --- a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.function.nf.test.snap @@ -1,25 +1,41 @@ { "Test Function checkProfileProvided": { "content": null, - "timestamp": "2024-02-09T15:43:55.145717" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:03.360873" }, "Test Function checkConfigProvided": { "content": [ true ], - "timestamp": "2024-01-19T11:34:13.548431224" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:02:59.729647" }, "Test Function nfCoreLogo": { "content": [ "\n\n-\u001b[2m----------------------------------------------------\u001b[0m-\n \u001b[0;32m,--.\u001b[0;30m/\u001b[0;32m,-.\u001b[0m\n\u001b[0;34m ___ __ __ __ ___ \u001b[0;32m/,-._.--~'\u001b[0m\n\u001b[0;34m |\\ | |__ __ / ` / \\ |__) |__ \u001b[0;33m} {\u001b[0m\n\u001b[0;34m | \\| | \\__, \\__/ | \\ |___ \u001b[0;32m\\`-._,-`-,\u001b[0m\n \u001b[0;32m`._,._,'\u001b[0m\n\u001b[0;35m nextflow_workflow v9.9.9\u001b[0m\n-\u001b[2m----------------------------------------------------\u001b[0m-\n" ], - "timestamp": "2024-01-19T11:34:38.840454873" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:10.562934" }, "Test Function workflowCitation": { "content": [ "If you use nextflow_workflow for your analysis please cite:\n\n* The pipeline\n https://doi.org/10.5281/zenodo.5070524\n\n* The nf-core framework\n https://doi.org/10.1038/s41587-020-0439-x\n\n* Software dependencies\n https://github.com/nextflow_workflow/blob/master/CITATIONS.md" ], - "timestamp": "2024-01-19T11:34:22.24352016" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:07.019761" }, "Test Function without logColours": { "content": [ @@ -73,13 +89,21 @@ "biwhite": "" } ], - "timestamp": "2024-01-19T11:35:04.418416984" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:17.969323" }, "Test Function dashedLine": { "content": [ "-\u001b[2m----------------------------------------------------\u001b[0m-" ], - "timestamp": "2024-01-19T11:34:55.420000755" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:14.366181" }, "Test Function with logColours": { "content": [ @@ -133,6 +157,10 @@ "biwhite": "\u001b[1;97m" } ], - "timestamp": "2024-01-19T11:35:13.436366565" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:21.714424" } } \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap index d07ce54c..859d1030 100644 --- a/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap +++ b/subworkflows/nf-core/utils_nfcore_pipeline/tests/main.workflow.nf.test.snap @@ -10,6 +10,10 @@ ] } ], - "timestamp": "2024-01-19T11:35:22.538940073" + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-28T12:03:25.726491" } } \ No newline at end of file diff --git a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test index 517ee54e..5784a33f 100644 --- a/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test +++ b/subworkflows/nf-core/utils_nfvalidation_plugin/tests/main.nf.test @@ -197,4 +197,4 @@ nextflow_workflow { ) } } -} \ No newline at end of file +} From 35dc9737fb68906e1ae664765411c06eb36805d2 Mon Sep 17 00:00:00 2001 From: EC2 Default User Date: Mon, 4 Mar 2024 17:23:34 +0000 Subject: [PATCH 31/49] version bump --- .nf-test.log | 17 +++ modules.json | 70 ++++++--- .../nf-core/kallistobustools/count/main.nf | 18 ++- .../kallistobustools/count/tests/main.nf.test | 98 +++++++++++++ .../count/tests/main.nf.test.snap | 100 +++++++++++++ .../count/tests/nextflow.config | 5 + .../kallistobustools/count/tests/tags.yml | 2 + modules/nf-core/kallistobustools/ref/main.nf | 28 ++++ .../kallistobustools/ref/tests/main.nf.test | 120 ++++++++++++++++ .../ref/tests/main.nf.test.snap | 136 ++++++++++++++++++ .../kallistobustools/ref/tests/tags.yml | 2 + tests/.nf-test.log | 21 +++ 12 files changed, 595 insertions(+), 22 deletions(-) create mode 100644 .nf-test.log create mode 100644 modules/nf-core/kallistobustools/count/tests/main.nf.test create mode 100644 modules/nf-core/kallistobustools/count/tests/main.nf.test.snap create mode 100644 modules/nf-core/kallistobustools/count/tests/nextflow.config create mode 100644 modules/nf-core/kallistobustools/count/tests/tags.yml create mode 100644 modules/nf-core/kallistobustools/ref/tests/main.nf.test create mode 100644 modules/nf-core/kallistobustools/ref/tests/main.nf.test.snap create mode 100644 modules/nf-core/kallistobustools/ref/tests/tags.yml create mode 100644 tests/.nf-test.log diff --git a/.nf-test.log b/.nf-test.log new file mode 100644 index 00000000..ca137888 --- /dev/null +++ b/.nf-test.log @@ -0,0 +1,17 @@ +Feb-27 21:54:16.881 [main] INFO com.askimed.nf.test.App - nf-test 0.8.4 +Feb-27 21:54:16.895 [main] INFO com.askimed.nf.test.App - Arguments: [test, tests/main_pipeline_kallisto.test, --update-snapshot] +Feb-27 21:54:17.590 [main] INFO com.askimed.nf.test.App - Nextflow Version: 23.10.1 +Feb-27 21:54:17.592 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Load config from file /home/ec2-user/scrnaseq/nf-test.config... +Feb-27 21:54:17.887 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Detected 1 test files. +Feb-27 21:54:18.162 [main] INFO com.askimed.nf.test.config.FileStaging - Copy directory '/home/ec2-user/scrnaseq/bin' to '/home/ec2-user/scrnaseq/.nf-test/tests/72e0d0f6b834ab79755c0f97ef8c4ca8/meta/bin' +Feb-27 21:54:18.164 [main] INFO com.askimed.nf.test.config.FileStaging - Copy directory '/home/ec2-user/scrnaseq/lib' to '/home/ec2-user/scrnaseq/.nf-test/tests/72e0d0f6b834ab79755c0f97ef8c4ca8/meta/lib' +Feb-27 21:54:18.164 [main] INFO com.askimed.nf.test.config.FileStaging - Copy directory '/home/ec2-user/scrnaseq/assets' to '/home/ec2-user/scrnaseq/.nf-test/tests/72e0d0f6b834ab79755c0f97ef8c4ca8/meta/assets' +Feb-27 21:54:18.171 [main] DEBUG com.askimed.nf.test.core.AbstractTest - Stage 0 user provided files... +Feb-27 21:54:18.174 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Started test plan +Feb-27 21:54:18.174 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Running testsuite 'Test Workflow main.nf' from file '/home/ec2-user/scrnaseq/tests/main_pipeline_kallisto.test'. +Feb-27 21:54:18.174 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Run test '72e0d0f6: test-dataset_kallisto_aligner'. type: com.askimed.nf.test.lang.pipeline.PipelineTest +Feb-27 21:55:36.281 [main] DEBUG com.askimed.nf.test.lang.extensions.SnapshotFile - Load snapshots from file '/home/ec2-user/scrnaseq/tests/main_pipeline_kallisto.test.snap' +Feb-27 21:55:36.305 [main] DEBUG com.askimed.nf.test.lang.extensions.Snapshot - Snapshots 'test-dataset_kallisto_aligner' match. +Feb-27 21:55:36.306 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Test '72e0d0f6: test-dataset_kallisto_aligner' finished. status: PASSED +Feb-27 21:55:36.308 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Testsuite 'Test Workflow main.nf' finished. snapshot file: true, skipped tests: false, failed tests: false +Feb-27 21:55:36.308 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Executed 1 tests. 0 tests failed. Done! diff --git a/modules.json b/modules.json index c71a0499..51864fc4 100644 --- a/modules.json +++ b/modules.json @@ -8,85 +8,117 @@ "cellranger/count": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cellranger/mkgtf": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cellranger/mkref": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cellrangerarc/count": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cellrangerarc/mkgtf": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "cellrangerarc/mkref": { "branch": "master", "git_sha": "4196b1b2e7ce265892f3979eabf7a9ddc030702f", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "custom/dumpsoftwareversions": { "branch": "master", "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "fastqc": { "branch": "master", "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "gffread": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "gunzip": { "branch": "master", "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "kallistobustools/count": { "branch": "master", - "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": ["modules"] + "git_sha": "de8215983defba48cd81961d620a9e844f11c7e7", + "installed_by": [ + "modules" + ] }, "kallistobustools/ref": { "branch": "master", - "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": ["modules"] + "git_sha": "de8215983defba48cd81961d620a9e844f11c7e7", + "installed_by": [ + "modules" + ] }, "multiqc": { "branch": "master", "git_sha": "9e71d8519dfbfc328c078bba14d4bd4c99e39a94", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "star/genomegenerate": { "branch": "master", "git_sha": "a21faa6a3481af92a343a10926f59c189a2c16c9", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "universc": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] }, "unzip": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": ["modules"] + "installed_by": [ + "modules" + ] } } } } } -} +} \ No newline at end of file diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf index 67ad5812..841ea2fe 100644 --- a/modules/nf-core/kallistobustools/count/main.nf +++ b/modules/nf-core/kallistobustools/count/main.nf @@ -17,9 +17,9 @@ process KALLISTOBUSTOOLS_COUNT { val workflow_mode output: - tuple val(meta), path ("*.count"), emit: count - path "versions.yml" , emit: versions - path "*.count/*/*.mtx" , emit: matrix //Ensure that kallisto finished and produced outputs + tuple val(meta), path ("*.count") , emit: count + path "versions.yml" , emit: versions + path "*.count/*/*.mtx" , emit: matrix //Ensure that kallisto finished and produced outputs when: task.ext.when == null || task.ext.when @@ -50,4 +50,16 @@ process KALLISTOBUSTOOLS_COUNT { kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//') END_VERSIONS """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + mkdir -p ${prefix}.count/counts_unfiltered/ + touch ${prefix}.count/counts_unfiltered/cells_x_genes.mtx + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//') + END_VERSIONS + """ } diff --git a/modules/nf-core/kallistobustools/count/tests/main.nf.test b/modules/nf-core/kallistobustools/count/tests/main.nf.test new file mode 100644 index 00000000..550001f9 --- /dev/null +++ b/modules/nf-core/kallistobustools/count/tests/main.nf.test @@ -0,0 +1,98 @@ +nextflow_process { + + name "Test Process KALLISTOBUSTOOLS_COUNT" + script "../main.nf" + process "KALLISTOBUSTOOLS_COUNT" + + tag "modules" + tag "modules_nfcore" + tag "kallistobustools" + tag "kallistobustools/count" + tag "kallistobustools/ref" + + setup { + run("KALLISTOBUSTOOLS_REF") { + script "../../ref/main.nf" + process { + """ + input[0] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + input[1] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) + input[2] = "standard" + """ + } + } + } + + test("genome.fasta + genome.gtf + '10X3' + 'standard'") { + + when { + process { + """ + input[0] = Channel.of( + [ + [id:'test'], // meta map + [ + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R1_001.fastq.gz', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R2_001.fastq.gz', checkIfExists: true) + ] + ] + ) + input[1] = KALLISTOBUSTOOLS_REF.out.index + input[2] = KALLISTOBUSTOOLS_REF.out.t2g + input[3] = KALLISTOBUSTOOLS_REF.out.cdna_t2c.ifEmpty{ [] } // when empty the module doesn't run unless something is passed. + input[4] = KALLISTOBUSTOOLS_REF.out.intron_t2c.ifEmpty{ [] } // when empty the module doesn't run unless something is passed. + input[5] = "10XV3" + input[6] = "standard" + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.versions, + process.out.matrix, + path(process.out.count.get(0).get(1)).list().findAll { file(it.toString()).name != "run_info.json" && file(it.toString()).name != "kb_info.json" }, + file(path(process.out.count.get(0).get(1)).list().find { file(it.toString()).name == "kb_info.json" }.toString()).readLines()[15..22], + file(path(process.out.count.get(0).get(1)).list().find { file(it.toString()).name == "run_info.json" }.toString()).readLines()[0..9] + ).match() + } + ) + } + } + + test("genome.fasta + genome.gtf + '10X3' + 'standard' - stub") { + + options "-stub" + + when { + process { + """ + input[0] = Channel.of( + [ + [id:'test'], // meta map + [ + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R1_001.fastq.gz', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R2_001.fastq.gz', checkIfExists: true) + ] + ] + ) + input[1] = KALLISTOBUSTOOLS_REF.out.index + input[2] = KALLISTOBUSTOOLS_REF.out.t2g + input[3] = KALLISTOBUSTOOLS_REF.out.cdna_t2c.ifEmpty{ [] } // when empty the module doesn't run unless something is passed. + input[4] = KALLISTOBUSTOOLS_REF.out.intron_t2c.ifEmpty{ [] } // when empty the module doesn't run unless something is passed. + input[5] = "10XV3" + input[6] = "standard" + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } +} diff --git a/modules/nf-core/kallistobustools/count/tests/main.nf.test.snap b/modules/nf-core/kallistobustools/count/tests/main.nf.test.snap new file mode 100644 index 00000000..3378c3c1 --- /dev/null +++ b/modules/nf-core/kallistobustools/count/tests/main.nf.test.snap @@ -0,0 +1,100 @@ +{ + "genome.fasta + genome.gtf + '10X3' + 'standard' - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test" + }, + [ + [ + "cells_x_genes.mtx:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ] + ] + ], + "1": [ + "versions.yml:md5,6ec06270afe0a7572c41567160d927d9" + ], + "2": [ + "cells_x_genes.mtx:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "count": [ + [ + { + "id": "test" + }, + [ + [ + "cells_x_genes.mtx:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ] + ] + ], + "matrix": [ + "cells_x_genes.mtx:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "versions": [ + "versions.yml:md5,6ec06270afe0a7572c41567160d927d9" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-03-01T15:48:45.775904562" + }, + "genome.fasta + genome.gtf + '10X3' + 'standard'": { + "content": [ + [ + "versions.yml:md5,6ec06270afe0a7572c41567160d927d9" + ], + [ + "cells_x_genes.mtx:md5,e12a45e7f7d6527f698dd9cb2e99ecd1" + ], + [ + "10x_version3_whitelist.txt:md5,3d36d0a4021fd292b265e2b5e72aaaf3", + [ + "cells_x_genes.barcodes.txt:md5,41f7adaf43b60f2f4f62d6a7073688de", + "cells_x_genes.genes.names.txt:md5,b29afa75be300c7f24fbd0740a66689b", + "cells_x_genes.genes.txt:md5,fe6d5501923867b514a0447aa4b4995f", + "cells_x_genes.mtx:md5,e12a45e7f7d6527f698dd9cb2e99ecd1" + ], + "inspect.json:md5,bafb47a58ac1bbf9be953f21c361d266", + "matrix.ec:md5,31a4c1a3e8e0c562b12f6569ffbf5459", + "output.bus:md5,d6fa0612a4a16eaf8a3e08bdc13ff49c", + "output.unfiltered.bus:md5,bf899b967657f612ba864188868d58cc", + "transcripts.txt:md5,23861cf43033e7c596e6989a88a3a373" + ], + [ + " \"commands\": [", + " \"kallisto bus -i kb_ref_out.idx -o test.count -x 10XV3 -t 2 subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R1_001.fastq.gz subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R2_001.fastq.gz\",", + " \"bustools sort -o test.count/tmp/output.s.bus -T test.count/tmp -t 2 -m 2G test.count/output.bus\",", + " \"bustools inspect -o test.count/inspect.json -w test.count/10x_version3_whitelist.txt test.count/tmp/output.s.bus\",", + " \"bustools correct -o test.count/tmp/output.s.c.bus -w test.count/10x_version3_whitelist.txt test.count/tmp/output.s.bus\",", + " \"bustools sort -o test.count/output.unfiltered.bus -T test.count/tmp -t 2 -m 2G test.count/tmp/output.s.c.bus\",", + " \"bustools count -o test.count/counts_unfiltered/cells_x_genes -g t2g.txt -e test.count/matrix.ec -t test.count/transcripts.txt --genecounts --umi-gene test.count/output.unfiltered.bus\"", + " ]," + ], + [ + "{", + "\t\"n_targets\": 12,", + "\t\"n_bootstraps\": 0,", + "\t\"n_processed\": 10000,", + "\t\"n_pseudoaligned\": 26,", + "\t\"n_unique\": 26,", + "\t\"p_pseudoaligned\": 0.3,", + "\t\"p_unique\": 0.3,", + "\t\"kallisto_version\": \"0.50.1\",", + "\t\"index_version\": 13," + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-03-01T15:48:24.476953631" + } +} \ No newline at end of file diff --git a/modules/nf-core/kallistobustools/count/tests/nextflow.config b/modules/nf-core/kallistobustools/count/tests/nextflow.config new file mode 100644 index 00000000..7a5cbfb4 --- /dev/null +++ b/modules/nf-core/kallistobustools/count/tests/nextflow.config @@ -0,0 +1,5 @@ +process { + withName: KALLISTOBUSTOOLS_COUNT { + ext.args = '--cellranger -m 1' + } +} diff --git a/modules/nf-core/kallistobustools/count/tests/tags.yml b/modules/nf-core/kallistobustools/count/tests/tags.yml new file mode 100644 index 00000000..9c432071 --- /dev/null +++ b/modules/nf-core/kallistobustools/count/tests/tags.yml @@ -0,0 +1,2 @@ +kallistobustools/count: + - "modules/nf-core/kallistobustools/count/**" diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf index 702317d3..0b45203d 100644 --- a/modules/nf-core/kallistobustools/ref/main.nf +++ b/modules/nf-core/kallistobustools/ref/main.nf @@ -62,4 +62,32 @@ process KALLISTOBUSTOOLS_REF { END_VERSIONS """ } + + stub: + if (workflow_mode == "standard") { + """ + touch kb_ref_out.idx \\ + touch t2g.txt \\ + touch cdna.fa + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//') + END_VERSIONS + """ + } else { + """ + touch kb_ref_out.idx \\ + touch t2g.txt \\ + touch cdna.fa + touch intron.fa \\ + touch cdna_t2c.txt \\ + touch intron_t2c.txt + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//') + END_VERSIONS + """ + } } diff --git a/modules/nf-core/kallistobustools/ref/tests/main.nf.test b/modules/nf-core/kallistobustools/ref/tests/main.nf.test new file mode 100644 index 00000000..dc49d9ac --- /dev/null +++ b/modules/nf-core/kallistobustools/ref/tests/main.nf.test @@ -0,0 +1,120 @@ +nextflow_process { + + name "Test Process KALLISTOBUSTOOLS_REF" + script "../main.nf" + process "KALLISTOBUSTOOLS_REF" + + tag "modules" + tag "modules_nfcore" + tag "kallistobustools" + tag "kallistobustools/ref" + + test("genome.fasta + genome.gtf + 'standard'") { + + when { + process { + """ + input[0] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + input[1] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) + input[2] = "standard" + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.versions, + process.out.t2g, + process.out.cdna, + process.out.intron, + process.out.cdna_t2c, + process.out.intron_t2c, + ).match() + }, + { assert file(process.out.index.get(0)).exists() } + ) + } + } + + test("genome.fasta + genome.gtf + 'nac'") { + + when { + process { + """ + input[0] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + input[1] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) + input[2] = "nac" + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.versions, + process.out.t2g, + process.out.cdna, + process.out.intron, + process.out.cdna_t2c, + process.out.intron_t2c, + ).match() + }, + { assert file(process.out.index.get(0)).exists() } + ) + } + } + + test("genome.fasta + genome.gtf + 'standard' - stub") { + + options "-stub" + + when { + process { + """ + input[0] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + input[1] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) + input[2] = "standard" + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } + + test("genome.fasta + genome.gtf + 'nac' - stub") { + + when { + process { + """ + input[0] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + input[1] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true) + input[2] = "nac" + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot( + process.out.versions, + process.out.t2g, + process.out.cdna, + process.out.intron, + process.out.cdna_t2c, + process.out.intron_t2c, + ).match() + }, + { assert file(process.out.index.get(0)).exists() } + ) + } + } +} diff --git a/modules/nf-core/kallistobustools/ref/tests/main.nf.test.snap b/modules/nf-core/kallistobustools/ref/tests/main.nf.test.snap new file mode 100644 index 00000000..9c2be8a7 --- /dev/null +++ b/modules/nf-core/kallistobustools/ref/tests/main.nf.test.snap @@ -0,0 +1,136 @@ +{ + "genome.fasta + genome.gtf + 'standard'": { + "content": [ + [ + "versions.yml:md5,d3d08c3c5638ae540965f77b8178b3c1" + ], + [ + "t2g.txt:md5,d1a8a22c59b9cb0bda39c0c9bb3f6afe" + ], + [ + "cdna.fa:md5,7bca59288fab822451de250d2eee48dc" + ], + [ + + ], + [ + + ], + [ + + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T23:37:43.739374859" + }, + "genome.fasta + genome.gtf + 'nac'": { + "content": [ + [ + "versions.yml:md5,d3d08c3c5638ae540965f77b8178b3c1" + ], + [ + "t2g.txt:md5,58591306b33bb948bac7b40f346d0cd7" + ], + [ + "cdna.fa:md5,7bca59288fab822451de250d2eee48dc" + ], + [ + "intron.fa:md5,1aad4e3f5d006f495cc6647fa0bbf6ff" + ], + [ + "cdna_t2c.txt:md5,23861cf43033e7c596e6989a88a3a373" + ], + [ + "intron_t2c.txt:md5,fe6d5501923867b514a0447aa4b4995f" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T23:37:59.436989671" + }, + "genome.fasta + genome.gtf + 'standard' - stub": { + "content": [ + { + "0": [ + "versions.yml:md5,d3d08c3c5638ae540965f77b8178b3c1" + ], + "1": [ + "kb_ref_out.idx:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "2": [ + "t2g.txt:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "3": [ + "cdna.fa:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "4": [ + + ], + "5": [ + + ], + "6": [ + + ], + "cdna": [ + "cdna.fa:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "cdna_t2c": [ + + ], + "index": [ + "kb_ref_out.idx:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "intron": [ + + ], + "intron_t2c": [ + + ], + "t2g": [ + "t2g.txt:md5,d41d8cd98f00b204e9800998ecf8427e" + ], + "versions": [ + "versions.yml:md5,d3d08c3c5638ae540965f77b8178b3c1" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T23:38:09.578411047" + }, + "genome.fasta + genome.gtf + 'nac' - stub": { + "content": [ + [ + "versions.yml:md5,d3d08c3c5638ae540965f77b8178b3c1" + ], + [ + "t2g.txt:md5,58591306b33bb948bac7b40f346d0cd7" + ], + [ + "cdna.fa:md5,7bca59288fab822451de250d2eee48dc" + ], + [ + "intron.fa:md5,1aad4e3f5d006f495cc6647fa0bbf6ff" + ], + [ + "cdna_t2c.txt:md5,23861cf43033e7c596e6989a88a3a373" + ], + [ + "intron_t2c.txt:md5,fe6d5501923867b514a0447aa4b4995f" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-02-29T23:38:25.355912473" + } +} \ No newline at end of file diff --git a/modules/nf-core/kallistobustools/ref/tests/tags.yml b/modules/nf-core/kallistobustools/ref/tests/tags.yml new file mode 100644 index 00000000..208c8d27 --- /dev/null +++ b/modules/nf-core/kallistobustools/ref/tests/tags.yml @@ -0,0 +1,2 @@ +kallistobustools/ref: + - "modules/nf-core/kallistobustools/ref/**" diff --git a/tests/.nf-test.log b/tests/.nf-test.log new file mode 100644 index 00000000..8251fc75 --- /dev/null +++ b/tests/.nf-test.log @@ -0,0 +1,21 @@ +Feb-27 21:54:09.971 [main] INFO com.askimed.nf.test.App - nf-test 0.8.4 +Feb-27 21:54:09.988 [main] INFO com.askimed.nf.test.App - Arguments: [test, tests/main_pipeline_kallisto.test, --update-snapshot] +Feb-27 21:54:10.670 [main] INFO com.askimed.nf.test.App - Nextflow Version: 23.10.1 +Feb-27 21:54:10.674 [main] WARN com.askimed.nf.test.commands.RunTestsCommand - No nf-test config file found. +Feb-27 21:54:10.674 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Detected 1 test files. +Feb-27 21:54:10.676 [main] ERROR com.askimed.nf.test.commands.RunTestsCommand - Running tests failed. +java.lang.Exception: Test file '/home/ec2-user/scrnaseq/tests/tests/main_pipeline_kallisto.test' not found. + at com.askimed.nf.test.core.TestExecutionEngine.parse(TestExecutionEngine.java:116) + at com.askimed.nf.test.core.TestExecutionEngine.execute(TestExecutionEngine.java:159) + at com.askimed.nf.test.commands.RunTestsCommand.execute(RunTestsCommand.java:184) + at com.askimed.nf.test.commands.AbstractCommand.call(AbstractCommand.java:43) + at com.askimed.nf.test.commands.AbstractCommand.call(AbstractCommand.java:18) + at picocli.CommandLine.executeUserObject(CommandLine.java:1953) + at picocli.CommandLine.access$1300(CommandLine.java:145) + at picocli.CommandLine$RunLast.executeUserObjectOfLastSubcommandWithSameParent(CommandLine.java:2352) + at picocli.CommandLine$RunLast.handle(CommandLine.java:2346) + at picocli.CommandLine$RunLast.handle(CommandLine.java:2311) + at picocli.CommandLine$AbstractParseResultHandler.execute(CommandLine.java:2179) + at picocli.CommandLine.execute(CommandLine.java:2078) + at com.askimed.nf.test.App.run(App.java:44) + at com.askimed.nf.test.App.main(App.java:51) From f12cfbbdc89ed0b65737c689f1ef80f7c4e51bdb Mon Sep 17 00:00:00 2001 From: nf-core-bot Date: Mon, 4 Mar 2024 19:14:39 +0000 Subject: [PATCH 32/49] [automated] Fix linting with Prettier --- modules.json | 66 ++++++++++++++-------------------------------------- 1 file changed, 17 insertions(+), 49 deletions(-) diff --git a/modules.json b/modules.json index 51864fc4..f6ae83cd 100644 --- a/modules.json +++ b/modules.json @@ -8,117 +8,85 @@ "cellranger/count": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellranger/mkgtf": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellranger/mkref": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellrangerarc/count": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellrangerarc/mkgtf": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellrangerarc/mkref": { "branch": "master", "git_sha": "4196b1b2e7ce265892f3979eabf7a9ddc030702f", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "custom/dumpsoftwareversions": { "branch": "master", "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "fastqc": { "branch": "master", "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "gffread": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "gunzip": { "branch": "master", "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "kallistobustools/count": { "branch": "master", "git_sha": "de8215983defba48cd81961d620a9e844f11c7e7", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "kallistobustools/ref": { "branch": "master", "git_sha": "de8215983defba48cd81961d620a9e844f11c7e7", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "multiqc": { "branch": "master", "git_sha": "9e71d8519dfbfc328c078bba14d4bd4c99e39a94", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "star/genomegenerate": { "branch": "master", "git_sha": "a21faa6a3481af92a343a10926f59c189a2c16c9", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "universc": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "unzip": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] } } } } } -} \ No newline at end of file +} From 5da76822f06416677c2cc1e81b0b0ccb8d984a89 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Wed, 6 Mar 2024 16:34:16 +0100 Subject: [PATCH 33/49] WIP cleanup after tempalte update --- README.md | 4 +- assets/schema_input.json | 28 ++++++- workflows/scrnaseq.nf | 174 +++++++++++++++------------------------ 3 files changed, 92 insertions(+), 114 deletions(-) diff --git a/README.md b/README.md index 23061375..3399f168 100644 --- a/README.md +++ b/README.md @@ -48,8 +48,8 @@ First, prepare a samplesheet with your input data that looks as follows: ```csv sample,fastq_1,fastq_2,expected_cells -pbmc8k,pbmc8k_S1_L007_R1_001.fastq.gz,pbmc8k_S1_L007_R2_001.fastq.gz,"10000" -pbmc8k,pbmc8k_S1_L008_R1_001.fastq.gz,pbmc8k_S1_L008_R2_001.fastq.gz,"10000" +pbmc8k,pbmc8k_S1_L007_R1_001.fastq.gz,pbmc8k_S1_L007_R2_001.fastq.gz,10000 +pbmc8k,pbmc8k_S1_L008_R1_001.fastq.gz,pbmc8k_S1_L008_R2_001.fastq.gz,10000 ``` Each row represents a fastq file (single-end) or a pair of fastq files (paired end). diff --git a/assets/schema_input.json b/assets/schema_input.json index dab0450a..490c54a7 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -11,7 +11,9 @@ "type": "string", "pattern": "^\\S+$", "errorMessage": "Sample name must be provided and cannot contain spaces", - "meta": ["id"] + "meta": [ + "id" + ] }, "fastq_1": { "type": "string", @@ -26,8 +28,28 @@ "exists": true, "pattern": "^\\S+\\.f(ast)?q\\.gz$", "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'" + }, + "expected_cells": { + "type": "integer", + "errorMessage": "Expected cells must be an Integer", + "meta": "expected_cells" + }, + "seq_center": { + "type": "string", + "meta": "seq_center" + }, + "sample_type": { + "type": "string", + "enum": [ + "atac", + "gex" + ] } }, - "required": ["sample", "fastq_1"] + "required": [ + "sample", + "fastq_1", + "fastq_2" + ] } -} +} \ No newline at end of file diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 6801d4dc..77cd1d20 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -4,126 +4,87 @@ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { FASTQC } from '../modules/nf-core/fastqc/main' -include { MULTIQC } from '../modules/nf-core/multiqc/main' -include { paramsSummaryMap } from 'plugin/nf-validation' -include { paramsSummaryMultiqc } from '../subworkflows/nf-core/utils_nfcore_pipeline' +include { MULTIQC } from '../modules/nf-core/multiqc/main' + +include { INPUT_CHECK } from '../subworkflows/local/input_check' +include { FASTQC_CHECK } from '../subworkflows/local/fastqc' +include { KALLISTO_BUSTOOLS } from '../subworkflows/local/kallisto_bustools' +include { SCRNASEQ_ALEVIN } from '../subworkflows/local/alevin' +include { STARSOLO } from '../subworkflows/local/starsolo' +include { CELLRANGER_ALIGN } from "../subworkflows/local/align_cellranger" +include { CELLRANGERARC_ALIGN } from "../subworkflows/local/align_cellrangerarc" +include { UNIVERSC_ALIGN } from "../subworkflows/local/align_universc" +include { MTX_CONVERSION } from "../subworkflows/local/mtx_conversion" +include { GTF_GENE_FILTER } from '../modules/local/gtf_gene_filter' + +include { paramsSummaryMap } from 'plugin/nf-validation' +include { paramsSummaryMultiqc } from '../subworkflows/nf-core/utils_nfcore_pipeline' include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline' include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_scrnaseq_pipeline' include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' -def summary_params = paramsSummaryMap(workflow) - -def checkPathParamList = [ - params.input, params.multiqc_config, params.fasta, params.gtf, - params.transcript_fasta, params.salmon_index, params.kallisto_index, - params.star_index, params.txp2gene, params.barcode_whitelist, params.cellranger_index, - params.universc_index -] -for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } } -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - CONFIG FILES -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) -ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath( params.multiqc_config, checkIfExists: true ) : Channel.empty() -ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath( params.multiqc_logo, checkIfExists: true ) : Channel.empty() -ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - IMPORT LOCAL MODULES/SUBWORKFLOWS -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -// -// SUBWORKFLOW: Consisting of a mix of local and nf-core/modules -// -include { INPUT_CHECK } from '../subworkflows/local/input_check' -include { FASTQC_CHECK } from '../subworkflows/local/fastqc' -include { KALLISTO_BUSTOOLS } from '../subworkflows/local/kallisto_bustools' -include { SCRNASEQ_ALEVIN } from '../subworkflows/local/alevin' -include { STARSOLO } from '../subworkflows/local/starsolo' -include { CELLRANGER_ALIGN } from "../subworkflows/local/align_cellranger" -include { CELLRANGERARC_ALIGN } from "../subworkflows/local/align_cellrangerarc" -include { UNIVERSC_ALIGN } from "../subworkflows/local/align_universc" -include { MTX_CONVERSION } from "../subworkflows/local/mtx_conversion" -include { GTF_GENE_FILTER } from '../modules/local/gtf_gene_filter' - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - IMPORT NF-CORE MODULES/SUBWORKFLOWS -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -// -// MODULE: Installed directly from nf-core/modules -// -include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' -include { MULTIQC } from '../modules/nf-core/multiqc/main' -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - RUN MAIN WORKFLOW -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -// Info required for completion email and summary -// TODO: Are this channels still necessary? -ch_output_docs = file("$projectDir/docs/output.md", checkIfExists: true) -ch_output_docs_images = file("$projectDir/docs/images/", checkIfExists: true) -protocol_config = WorkflowScrnaseq.getProtocol(workflow, log, params.aligner, params.protocol) -if (protocol_config['protocol'] == 'auto' && params.aligner != "cellranger") { - error "Only cellranger supports `protocol = 'auto'`. Please specify the protocol manually!" -} +workflow SCRNASEQ { -// general input and params -ch_input = file(params.input) -ch_genome_fasta = Channel.value(params.fasta ? file(params.fasta) : []) -ch_gtf = params.gtf ? file(params.gtf) : [] -ch_transcript_fasta = params.transcript_fasta ? file(params.transcript_fasta): [] -ch_motifs = params.motifs ? file(params.motifs) : [] -ch_cellrangerarc_config = params.cellrangerarc_config ? file(params.cellrangerarc_config) : [] -ch_txp2gene = params.txp2gene ? file(params.txp2gene) : [] -ch_multiqc_alevin = Channel.empty() -ch_multiqc_star = Channel.empty() -ch_multiqc_cellranger = Channel.empty() -if (params.barcode_whitelist) { - ch_barcode_whitelist = file(params.barcode_whitelist) -} else if (protocol_config.containsKey("whitelist")) { - ch_barcode_whitelist = file("$projectDir/${protocol_config['whitelist']}") -} else { - ch_barcode_whitelist = [] -} + take: + ch_samplesheet // channel: samplesheet read in from --input + main: -//kallisto params -ch_kallisto_index = params.kallisto_index ? file(params.kallisto_index) : [] -kb_workflow = params.kb_workflow + // TODO: checks still necessary in favor of schema validation? + def checkPathParamList = [ + params.input, params.multiqc_config, params.fasta, params.gtf, + params.transcript_fasta, params.salmon_index, params.kallisto_index, + params.star_index, params.txp2gene, params.barcode_whitelist, params.cellranger_index, + params.universc_index + ] + for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } } + + // Info required for completion email and summary + // TODO: Are this channels still necessary? + protocol_config = WorkflowScrnaseq.getProtocol(workflow, log, params.aligner, params.protocol) + if (protocol_config['protocol'] == 'auto' && params.aligner != "cellranger") { + error "Only cellranger supports `protocol = 'auto'`. Please specify the protocol manually!" + } -//salmon params -ch_salmon_index = params.salmon_index ? file(params.salmon_index) : [] + // general input and params + ch_input = file(params.input) + ch_genome_fasta = Channel.value(params.fasta ? file(params.fasta) : []) + ch_gtf = params.gtf ? file(params.gtf) : [] + ch_transcript_fasta = params.transcript_fasta ? file(params.transcript_fasta): [] + ch_motifs = params.motifs ? file(params.motifs) : [] + ch_cellrangerarc_config = params.cellrangerarc_config ? file(params.cellrangerarc_config) : [] + ch_txp2gene = params.txp2gene ? file(params.txp2gene) : [] + ch_multiqc_alevin = Channel.empty() + ch_multiqc_star = Channel.empty() + ch_multiqc_cellranger = Channel.empty() + if (params.barcode_whitelist) { + ch_barcode_whitelist = file(params.barcode_whitelist) + } else if (protocol_config.containsKey("whitelist")) { + ch_barcode_whitelist = file("$projectDir/${protocol_config['whitelist']}") + } else { + ch_barcode_whitelist = [] + } -//star params -ch_star_index = params.star_index ? file(params.star_index) : [] -star_feature = params.star_feature -//cellranger params -ch_cellranger_index = params.cellranger_index ? file(params.cellranger_index) : [] + //kallisto params + ch_kallisto_index = params.kallisto_index ? file(params.kallisto_index) : [] + kb_workflow = params.kb_workflow -//universc params -ch_universc_index = params.universc_index ? file(params.universc_index) : [] + //salmon params + ch_salmon_index = params.salmon_index ? file(params.salmon_index) : [] -workflow SCRNASEQ { + //star params + ch_star_index = params.star_index ? file(params.star_index) : [] + star_feature = params.star_feature - take: - ch_samplesheet // channel: samplesheet read in from --input + //cellranger params + ch_cellranger_index = params.cellranger_index ? file(params.cellranger_index) : [] - main: + //universc params + ch_universc_index = params.universc_index ? file(params.universc_index) : [] ch_versions = Channel.empty() ch_mtx_matrices = Channel.empty() @@ -254,11 +215,6 @@ workflow SCRNASEQ { //Add Versions from MTX Conversion workflow too ch_versions.mix(MTX_CONVERSION.out.ch_versions) - // collect software versions - CUSTOM_DUMPSOFTWAREVERSIONS ( - ch_versions.unique().collectFile(name: 'collated_versions.yml') - ) - // // MODULE: MultiQC // @@ -270,7 +226,7 @@ workflow SCRNASEQ { ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) ch_methods_description = Channel.value(methodsDescriptionText(ch_multiqc_custom_methods_description)) ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(ch_collated_versions) + ch_multiqc_files = ch_multiqc_files.mix(softwareVersionsToYAML(ch_versions).collectFile(name: 'versions.yml')) ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml', sort: false)) MULTIQC ( From 070f12338df41a4449d1e00ae3fc3c2a8cf1fa5a Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 10:12:43 +0100 Subject: [PATCH 34/49] Move parameter validation to nextflow schema --- assets/schema_input.json | 13 +++++-- lib/WorkflowScrnaseq.groovy | 21 ++++++++++ main.nf | 40 ++++++++++--------- nextflow_schema.json | 74 ++++++++++++++++++++++++++++------- workflows/scrnaseq.nf | 77 +++++++++---------------------------- 5 files changed, 130 insertions(+), 95 deletions(-) create mode 100755 lib/WorkflowScrnaseq.groovy diff --git a/assets/schema_input.json b/assets/schema_input.json index 490c54a7..af6ccfa3 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -32,17 +32,24 @@ "expected_cells": { "type": "integer", "errorMessage": "Expected cells must be an Integer", - "meta": "expected_cells" + "meta": [ + "expected_cells" + ] }, "seq_center": { "type": "string", - "meta": "seq_center" + "meta": [ + "seq_center" + ] }, "sample_type": { "type": "string", "enum": [ "atac", "gex" + ], + "meta": [ + "sample_type" ] } }, @@ -52,4 +59,4 @@ "fastq_2" ] } -} \ No newline at end of file +} diff --git a/lib/WorkflowScrnaseq.groovy b/lib/WorkflowScrnaseq.groovy new file mode 100755 index 00000000..07475fe1 --- /dev/null +++ b/lib/WorkflowScrnaseq.groovy @@ -0,0 +1,21 @@ +import groovy.json.JsonSlurper + + +class WorkflowScrnaseq { + // Retrieve the aligner-specific protocol based on the specified protocol. + // Returns a map ["protocol": protocol, "extra_args": , "whitelist": ] + // extra_args and whitelist are optional. + public static Map getProtocol(workflow, log, aligner, protocol) { + def jsonSlurper = new JsonSlurper() + def json = new File("${workflow.projectDir}/assets/protocols.json").text + def protocols = jsonSlurper.parseText(json) + def aligner_map = protocols[aligner] + if(aligner_map.containsKey(protocol)) { + return aligner_map[protocol] + } else { + log.warn("Protocol '${protocol}' not recognized by the pipeline. Passing on the protocol to the aligner unmodified.") + return ["protocol": protocol] + } + } + +} diff --git a/main.nf b/main.nf index 3471e5b0..4f96908f 100644 --- a/main.nf +++ b/main.nf @@ -82,25 +82,27 @@ workflow { params.input ) - // - // WORKFLOW: Run main workflow - // - NFCORE_SCRNASEQ ( - PIPELINE_INITIALISATION.out.samplesheet - ) - - // - // SUBWORKFLOW: Run completion tasks - // - PIPELINE_COMPLETION ( - params.email, - params.email_on_fail, - params.plaintext_email, - params.outdir, - params.monochrome_logs, - params.hook_url, - NFCORE_SCRNASEQ.out.multiqc_report - ) + PIPELINE_INITIALISATION.out.samplesheet.view() + + // // + // // WORKFLOW: Run main workflow + // // + // NFCORE_SCRNASEQ ( + // PIPELINE_INITIALISATION.out.samplesheet.view() + // ) + + // // + // // SUBWORKFLOW: Run completion tasks + // // + // PIPELINE_COMPLETION ( + // params.email, + // params.email_on_fail, + // params.plaintext_email, + // params.outdir, + // params.monochrome_logs, + // params.hook_url, + // NFCORE_SCRNASEQ.out.multiqc_report + // ) } /* diff --git a/nextflow_schema.json b/nextflow_schema.json index 65b4b695..e9fef834 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -10,7 +10,10 @@ "type": "object", "fa_icon": "fas fa-terminal", "description": "Define where the pipeline should find input data and save output data.", - "required": ["input", "outdir"], + "required": [ + "input", + "outdir" + ], "properties": { "input": { "type": "string", @@ -51,7 +54,9 @@ "barcode_whitelist": { "type": "string", "description": "If not using the 10X Genomics platform, a custom barcode whitelist can be used with `--barcode_whitelist`.", - "fa_icon": "fas fa-barcode" + "fa_icon": "fas fa-barcode", + "format": "file-path", + "exists": true }, "aligner": { "type": "string", @@ -59,7 +64,14 @@ "default": "alevin", "help_text": "The workflow can handle three types of methods:\n\n- Kallisto/Bustools\n- Salmon Alevin + AlevinQC\n- STARsolo\n\nTo choose which one to use, please specify either `alevin`, `star` or `kallisto` as a parameter option for `--aligner`. By default, the pipeline runs the `alevin` option. Note that specifying another aligner option also requires choosing appropriate parameters (see below) for the selected option.", "fa_icon": "fas fa-align-center", - "enum": ["kallisto", "star", "alevin", "cellranger", "cellrangerarc", "universc"] + "enum": [ + "kallisto", + "star", + "alevin", + "cellranger", + "cellrangerarc", + "universc" + ] }, "protocol": { "type": "string", @@ -120,12 +132,16 @@ "transcript_fasta": { "type": "string", "description": "A cDNA FASTA file", - "fa_icon": "fas fa-dna" + "fa_icon": "fas fa-dna", + "format": "file-path", + "exists": true }, "gtf": { "type": "string", "description": "Reference GTF annotation file", - "fa_icon": "fas fa-code-branch" + "fa_icon": "fas fa-code-branch", + "format": "file-path", + "exists": true }, "save_reference": { "type": "boolean", @@ -151,13 +167,17 @@ "salmon_index": { "type": "string", "description": "This can be used to specify a precomputed Salmon index in the pipeline, in order to skip the generation of required indices by Salmon itself.", - "fa_icon": "fas fa-fish" + "fa_icon": "fas fa-fish", + "format": "file-path", + "exists": true }, "txp2gene": { "type": "string", "description": "Path to transcript to gene mapping file. This allows the specification of a transcript to gene mapping file for Salmon Alevin and AlevinQC.", "help_text": "> This is not the same as the `kallisto_gene_map` parameter down below and is only used by the Salmon Alevin workflow.", - "fa_icon": "fas fa-map-marked-alt" + "fa_icon": "fas fa-map-marked-alt", + "format": "file-path", + "exists": true }, "simpleaf_rlen": { "type": "integer", @@ -177,7 +197,9 @@ "type": "string", "description": "Specify a path to the precomputed STAR index.", "help_text": "> NB: This has to be computed with STAR Version 2.7 or later, as STARsolo was only first supported by STAR Version 2.7.", - "fa_icon": "fas fa-asterisk" + "fa_icon": "fas fa-asterisk", + "format": "file-path", + "exists": true }, "star_ignore_sjdbgtf": { "type": "string", @@ -190,7 +212,11 @@ "star_feature": { "type": "string", "default": "Gene", - "enum": ["Gene", "GeneFull", "Gene Velocyto"], + "enum": [ + "Gene", + "GeneFull", + "Gene Velocyto" + ], "description": "Quantification type of different transcriptomic feature. Use `GeneFull` on pre-mRNA count for single-nucleus RNA-seq reads. Use `Gene Velocyto` to generate RNA velocity matrix.", "fa_icon": "fas fa-asterisk" } @@ -212,14 +238,22 @@ "kallisto_index": { "type": "string", "description": "Specify a path to the precomputed Kallisto index.", - "fa_icon": "fas fa-fish" + "fa_icon": "fas fa-fish", + "format": "file-path", + "exists": true }, "kb_workflow": { "type": "string", "default": "standard", "description": "Type of workflow. Use `lamanno` for RNA velocity based on La Manno et al. 2018 logic. Use `nucleus` for RNA velocity on single-nucleus RNA-seq reads. Use `kite` for feature barcoding. Use `kite: 10xFB` for 10x Genomics Feature Barcoding technology. (default: standard)", "fa_icon": "fas fa-fish", - "enum": ["standard", "lamanno", "nucleus", "kite", "kite: 10xFB"] + "enum": [ + "standard", + "lamanno", + "nucleus", + "kite", + "kite: 10xFB" + ] } } }, @@ -231,7 +265,9 @@ "properties": { "cellranger_index": { "type": "string", - "description": "Specify a pre-calculated cellranger index. Readily prepared indexes can be obtained from the 10x Genomics website. " + "description": "Specify a pre-calculated cellranger index. Readily prepared indexes can be obtained from the 10x Genomics website. ", + "format": "file-path", + "exists": true } } }, @@ -263,7 +299,9 @@ "properties": { "universc_index": { "type": "string", - "description": "Specify a pre-calculated cellranger index. Readily prepared indexes can be obtained from the 10x Genomics website." + "description": "Specify a pre-calculated cellranger index. Readily prepared indexes can be obtained from the 10x Genomics website.", + "format": "file-path", + "exists": true } } }, @@ -375,7 +413,14 @@ "description": "Method used to save pipeline results to output directory.", "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.", "fa_icon": "fas fa-copy", - "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"], + "enum": [ + "symlink", + "rellink", + "link", + "copy", + "copyNoFollow", + "move" + ], "hidden": true }, "email_on_fail": { @@ -417,6 +462,7 @@ "type": "string", "format": "file-path", "description": "Custom config file to supply to MultiQC.", + "exists": true, "fa_icon": "fas fa-cog", "hidden": true }, diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 77cd1d20..916533c2 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -1,12 +1,4 @@ -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - IMPORT MODULES / SUBWORKFLOWS / FUNCTIONS -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - include { MULTIQC } from '../modules/nf-core/multiqc/main' - -include { INPUT_CHECK } from '../subworkflows/local/input_check' include { FASTQC_CHECK } from '../subworkflows/local/fastqc' include { KALLISTO_BUSTOOLS } from '../subworkflows/local/kallisto_bustools' include { SCRNASEQ_ALEVIN } from '../subworkflows/local/alevin' @@ -17,49 +9,33 @@ include { UNIVERSC_ALIGN } from "../subworkflows/local/align_universc" include { MTX_CONVERSION } from "../subworkflows/local/mtx_conversion" include { GTF_GENE_FILTER } from '../modules/local/gtf_gene_filter' -include { paramsSummaryMap } from 'plugin/nf-validation' include { paramsSummaryMultiqc } from '../subworkflows/nf-core/utils_nfcore_pipeline' include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline' include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_scrnaseq_pipeline' include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' - - workflow SCRNASEQ { take: - ch_samplesheet // channel: samplesheet read in from --input + ch_input // channel: samplesheet read in from --input main: + ch_fastq = Channel.empty() - // TODO: checks still necessary in favor of schema validation? - def checkPathParamList = [ - params.input, params.multiqc_config, params.fasta, params.gtf, - params.transcript_fasta, params.salmon_index, params.kallisto_index, - params.star_index, params.txp2gene, params.barcode_whitelist, params.cellranger_index, - params.universc_index - ] - for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } } - - // Info required for completion email and summary - // TODO: Are this channels still necessary? protocol_config = WorkflowScrnaseq.getProtocol(workflow, log, params.aligner, params.protocol) if (protocol_config['protocol'] == 'auto' && params.aligner != "cellranger") { error "Only cellranger supports `protocol = 'auto'`. Please specify the protocol manually!" } // general input and params - ch_input = file(params.input) ch_genome_fasta = Channel.value(params.fasta ? file(params.fasta) : []) ch_gtf = params.gtf ? file(params.gtf) : [] ch_transcript_fasta = params.transcript_fasta ? file(params.transcript_fasta): [] ch_motifs = params.motifs ? file(params.motifs) : [] ch_cellrangerarc_config = params.cellrangerarc_config ? file(params.cellrangerarc_config) : [] ch_txp2gene = params.txp2gene ? file(params.txp2gene) : [] - ch_multiqc_alevin = Channel.empty() - ch_multiqc_star = Channel.empty() - ch_multiqc_cellranger = Channel.empty() + ch_multiqc_files = Channel.empty() if (params.barcode_whitelist) { ch_barcode_whitelist = file(params.barcode_whitelist) } else if (protocol_config.containsKey("whitelist")) { @@ -68,7 +44,6 @@ workflow SCRNASEQ { ch_barcode_whitelist = [] } - //kallisto params ch_kallisto_index = params.kallisto_index ? file(params.kallisto_index) : [] kb_workflow = params.kb_workflow @@ -89,22 +64,11 @@ workflow SCRNASEQ { ch_versions = Channel.empty() ch_mtx_matrices = Channel.empty() - // Check input files and stage input data - ch_fastq = INPUT_CHECK( ch_input ).reads - - ch_versions = ch_versions.mix(INPUT_CHECK.out.versions) - // TODO: OPTIONAL, you can use nf-validation plugin to create an input channel from the samplesheet with Channel.fromSamplesheet("input") - // See the documentation https://nextflow-io.github.io/nf-validation/samplesheets/fromSamplesheet/ - // ! There is currently no tooling to help you write a sample sheet schema - // Run FastQC - ch_multiqc_fastqc = Channel.empty() if (!params.skip_fastqc) { FASTQC_CHECK ( ch_fastq ) ch_versions = ch_versions.mix(FASTQC_CHECK.out.fastqc_version) - ch_multiqc_fastqc = FASTQC_CHECK.out.fastqc_zip - } else { - ch_multiqc_fastqc = Channel.empty() + ch_multiqc_files = ch_multiqc_files.mix(FASTQC_CHECK.out.fastqc_zip) } ch_filter_gtf = GTF_GENE_FILTER ( ch_genome_fasta, ch_gtf ).gtf @@ -138,7 +102,7 @@ workflow SCRNASEQ { ch_fastq ) ch_versions = ch_versions.mix(SCRNASEQ_ALEVIN.out.ch_versions) - ch_multiqc_alevin = SCRNASEQ_ALEVIN.out.alevin_results + ch_multiqc_files = ch_multiqc_files.mix(SCRNASEQ_ALEVIN.out.alevin_results) ch_mtx_matrices = ch_mtx_matrices.mix(SCRNASEQ_ALEVIN.out.alevin_results) } @@ -157,7 +121,7 @@ workflow SCRNASEQ { ch_versions = ch_versions.mix(STARSOLO.out.ch_versions) ch_mtx_matrices = ch_mtx_matrices.mix(STARSOLO.out.star_counts) ch_star_index = STARSOLO.out.star_index - ch_multiqc_star = STARSOLO.out.for_multiqc + ch_multiqc_files = ch_multiqc_files.mix(STARSOLO.out.for_multiqc) } // Run cellranger pipeline @@ -172,9 +136,9 @@ workflow SCRNASEQ { ch_versions = ch_versions.mix(CELLRANGER_ALIGN.out.ch_versions) ch_mtx_matrices = ch_mtx_matrices.mix(CELLRANGER_ALIGN.out.cellranger_out) ch_star_index = CELLRANGER_ALIGN.out.star_index - ch_multiqc_cellranger = CELLRANGER_ALIGN.out.cellranger_out.map{ + ch_multiqc_files = ch_multiqc_files.mix(CELLRANGER_ALIGN.out.cellranger_out.map{ meta, outs -> outs.findAll{ it -> it.name == "web_summary.html"} - } + }) } // Run universc pipeline @@ -204,16 +168,17 @@ workflow SCRNASEQ { ch_mtx_matrices = ch_mtx_matrices.mix(CELLRANGERARC_ALIGN.out.cellranger_arc_out) } - // Run mtx to h5ad conversion subworkflow - MTX_CONVERSION ( - ch_mtx_matrices, - ch_input, - ch_txp2gene, - ch_star_index - ) + // TODO + // // Run mtx to h5ad conversion subworkflow + // MTX_CONVERSION ( + // ch_mtx_matrices, + // ch_input, + // ch_txp2gene, + // ch_star_index + // ) - //Add Versions from MTX Conversion workflow too - ch_versions.mix(MTX_CONVERSION.out.ch_versions) + // //Add Versions from MTX Conversion workflow too + // ch_versions.mix(MTX_CONVERSION.out.ch_versions) // // MODULE: MultiQC @@ -240,9 +205,3 @@ workflow SCRNASEQ { multiqc_report = MULTIQC.out.report.toList() // channel: /path/to/multiqc_report.html versions = ch_versions // channel: [ path(versions.yml) ] } - -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - THE END -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ From 94600114cc8cfdb60f6d9063f1f1b1ea8634f869 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 10:14:59 +0100 Subject: [PATCH 35/49] Enable workflow --- main.nf | 40 +++++++++++++++++++--------------------- workflows/scrnaseq.nf | 3 +-- 2 files changed, 20 insertions(+), 23 deletions(-) diff --git a/main.nf b/main.nf index 4f96908f..3471e5b0 100644 --- a/main.nf +++ b/main.nf @@ -82,27 +82,25 @@ workflow { params.input ) - PIPELINE_INITIALISATION.out.samplesheet.view() - - // // - // // WORKFLOW: Run main workflow - // // - // NFCORE_SCRNASEQ ( - // PIPELINE_INITIALISATION.out.samplesheet.view() - // ) - - // // - // // SUBWORKFLOW: Run completion tasks - // // - // PIPELINE_COMPLETION ( - // params.email, - // params.email_on_fail, - // params.plaintext_email, - // params.outdir, - // params.monochrome_logs, - // params.hook_url, - // NFCORE_SCRNASEQ.out.multiqc_report - // ) + // + // WORKFLOW: Run main workflow + // + NFCORE_SCRNASEQ ( + PIPELINE_INITIALISATION.out.samplesheet + ) + + // + // SUBWORKFLOW: Run completion tasks + // + PIPELINE_COMPLETION ( + params.email, + params.email_on_fail, + params.plaintext_email, + params.outdir, + params.monochrome_logs, + params.hook_url, + NFCORE_SCRNASEQ.out.multiqc_report + ) } /* diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 916533c2..ab1fa3a1 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -18,10 +18,9 @@ include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' workflow SCRNASEQ { take: - ch_input // channel: samplesheet read in from --input + ch_fastq main: - ch_fastq = Channel.empty() protocol_config = WorkflowScrnaseq.getProtocol(workflow, log, params.aligner, params.protocol) if (protocol_config['protocol'] == 'auto' && params.aligner != "cellranger") { From c78f4bbb1cc24afc18e2ee8afd59f553f00a083f Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 10:18:02 +0100 Subject: [PATCH 36/49] pre-commit --- assets/schema_input.json | 27 +++------- modules.json | 76 +++++++------------------- modules/nf-core/universc/CITATION.cff | 78 +++++++++++++-------------- nextflow_schema.json | 37 ++----------- workflows/scrnaseq.nf | 26 +++++---- 5 files changed, 84 insertions(+), 160 deletions(-) diff --git a/assets/schema_input.json b/assets/schema_input.json index af6ccfa3..a531769f 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -11,9 +11,7 @@ "type": "string", "pattern": "^\\S+$", "errorMessage": "Sample name must be provided and cannot contain spaces", - "meta": [ - "id" - ] + "meta": ["id"] }, "fastq_1": { "type": "string", @@ -32,31 +30,18 @@ "expected_cells": { "type": "integer", "errorMessage": "Expected cells must be an Integer", - "meta": [ - "expected_cells" - ] + "meta": ["expected_cells"] }, "seq_center": { "type": "string", - "meta": [ - "seq_center" - ] + "meta": ["seq_center"] }, "sample_type": { "type": "string", - "enum": [ - "atac", - "gex" - ], - "meta": [ - "sample_type" - ] + "enum": ["atac", "gex"], + "meta": ["sample_type"] } }, - "required": [ - "sample", - "fastq_1", - "fastq_2" - ] + "required": ["sample", "fastq_1", "fastq_2"] } } diff --git a/modules.json b/modules.json index d81f322c..e1234f4c 100644 --- a/modules.json +++ b/modules.json @@ -8,114 +8,82 @@ "cellranger/count": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellranger/mkgtf": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellranger/mkref": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellrangerarc/count": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellrangerarc/mkgtf": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "cellrangerarc/mkref": { "branch": "master", "git_sha": "4196b1b2e7ce265892f3979eabf7a9ddc030702f", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "custom/dumpsoftwareversions": { "branch": "master", "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "fastqc": { "branch": "master", "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "gffread": { "branch": "master", "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "gunzip": { "branch": "master", "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "kallistobustools/count": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "kallistobustools/ref": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "multiqc": { "branch": "master", "git_sha": "9e71d8519dfbfc328c078bba14d4bd4c99e39a94", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "star/genomegenerate": { "branch": "master", "git_sha": "a21faa6a3481af92a343a10926f59c189a2c16c9", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "universc": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] }, "unzip": { "branch": "master", "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5", - "installed_by": [ - "modules" - ] + "installed_by": ["modules"] } } }, @@ -124,23 +92,17 @@ "utils_nextflow_pipeline": { "branch": "master", "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", - "installed_by": [ - "subworkflows" - ] + "installed_by": ["subworkflows"] }, "utils_nfcore_pipeline": { "branch": "master", "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", - "installed_by": [ - "subworkflows" - ] + "installed_by": ["subworkflows"] }, "utils_nfvalidation_plugin": { "branch": "master", "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa", - "installed_by": [ - "subworkflows" - ] + "installed_by": ["subworkflows"] } } } diff --git a/modules/nf-core/universc/CITATION.cff b/modules/nf-core/universc/CITATION.cff index b00957d1..35e281e6 100644 --- a/modules/nf-core/universc/CITATION.cff +++ b/modules/nf-core/universc/CITATION.cff @@ -1,23 +1,6 @@ cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - - given-names: "S. Thomas" - family-names: "Kelly" - email: "tom.kelly@riken.jp" - affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" - orcid: "https://orcid.org/0000-0003-3904-6690" - - family-names: "Battenberg" - given-names: "Kai" - email: "kai.battenberg@riken.jp" - affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" - orcid: "http://orcid.org/0000-0001-7517-2657" -version: 1.2.5.1 -doi: 10.1101/2021.01.19.427209 -date-released: 2021-02-14 -url: "https://github.com/minoda-lab/universc" -preferred-citation: - type: article - authors: - given-names: "S. Thomas" family-names: "Kelly" email: "tom.kelly@riken.jp" @@ -27,25 +10,42 @@ preferred-citation: given-names: "Kai" email: "kai.battenberg@riken.jp" affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" - orcid: "https://orcid.org/http://orcid.org/0000-0001-7517-2657" - - family-names: "Hetherington" - given-names: "Nicola A." - affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" - orcid: "http://orcid.org/0000-0001-8802-2906" - - family-names: "Hayashi" - given-names: "Makoto" - affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" - orcid: "http://orcid.org/0000-0001-6389-4265" - - given-names: "Aki" - family-names: "Minoda" - email: "akiko.minoda@riken.jp" - affiliation: Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" - orcid: "http://orcid.org/0000-0002-2927-5791" - doi: "10.1101/2021.01.19.427209" - title: "UniverSC: a flexible cross-platform single-cell data processing pipeline" - year: "2021" - journal: "bioRxiv" - start: 2021.01.19.427209 - volume: - issue: - month: 1 + orcid: "http://orcid.org/0000-0001-7517-2657" +version: 1.2.5.1 +doi: 10.1101/2021.01.19.427209 +date-released: 2021-02-14 +url: "https://github.com/minoda-lab/universc" +preferred-citation: + type: article + authors: + - given-names: "S. Thomas" + family-names: "Kelly" + email: "tom.kelly@riken.jp" + affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" + orcid: "https://orcid.org/0000-0003-3904-6690" + - family-names: "Battenberg" + given-names: "Kai" + email: "kai.battenberg@riken.jp" + affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" + orcid: "https://orcid.org/http://orcid.org/0000-0001-7517-2657" + - family-names: "Hetherington" + given-names: "Nicola A." + affiliation: "Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" + orcid: "http://orcid.org/0000-0001-8802-2906" + - family-names: "Hayashi" + given-names: "Makoto" + affiliation: "Center for Sustainable Resource Science, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" + orcid: "http://orcid.org/0000-0001-6389-4265" + - given-names: "Aki" + family-names: "Minoda" + email: "akiko.minoda@riken.jp" + affiliation: Center for Integrative Medical Sciences, RIKEN, Suehiro-cho-1-7-22, Tsurumi Ward, Yokohama, Japan" + orcid: "http://orcid.org/0000-0002-2927-5791" + doi: "10.1101/2021.01.19.427209" + title: "UniverSC: a flexible cross-platform single-cell data processing pipeline" + year: "2021" + journal: "bioRxiv" + start: 2021.01.19.427209 + volume: + issue: + month: 1 diff --git a/nextflow_schema.json b/nextflow_schema.json index e9fef834..649b9b18 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -10,10 +10,7 @@ "type": "object", "fa_icon": "fas fa-terminal", "description": "Define where the pipeline should find input data and save output data.", - "required": [ - "input", - "outdir" - ], + "required": ["input", "outdir"], "properties": { "input": { "type": "string", @@ -64,14 +61,7 @@ "default": "alevin", "help_text": "The workflow can handle three types of methods:\n\n- Kallisto/Bustools\n- Salmon Alevin + AlevinQC\n- STARsolo\n\nTo choose which one to use, please specify either `alevin`, `star` or `kallisto` as a parameter option for `--aligner`. By default, the pipeline runs the `alevin` option. Note that specifying another aligner option also requires choosing appropriate parameters (see below) for the selected option.", "fa_icon": "fas fa-align-center", - "enum": [ - "kallisto", - "star", - "alevin", - "cellranger", - "cellrangerarc", - "universc" - ] + "enum": ["kallisto", "star", "alevin", "cellranger", "cellrangerarc", "universc"] }, "protocol": { "type": "string", @@ -212,11 +202,7 @@ "star_feature": { "type": "string", "default": "Gene", - "enum": [ - "Gene", - "GeneFull", - "Gene Velocyto" - ], + "enum": ["Gene", "GeneFull", "Gene Velocyto"], "description": "Quantification type of different transcriptomic feature. Use `GeneFull` on pre-mRNA count for single-nucleus RNA-seq reads. Use `Gene Velocyto` to generate RNA velocity matrix.", "fa_icon": "fas fa-asterisk" } @@ -247,13 +233,7 @@ "default": "standard", "description": "Type of workflow. Use `lamanno` for RNA velocity based on La Manno et al. 2018 logic. Use `nucleus` for RNA velocity on single-nucleus RNA-seq reads. Use `kite` for feature barcoding. Use `kite: 10xFB` for 10x Genomics Feature Barcoding technology. (default: standard)", "fa_icon": "fas fa-fish", - "enum": [ - "standard", - "lamanno", - "nucleus", - "kite", - "kite: 10xFB" - ] + "enum": ["standard", "lamanno", "nucleus", "kite", "kite: 10xFB"] } } }, @@ -413,14 +393,7 @@ "description": "Method used to save pipeline results to output directory.", "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.", "fa_icon": "fas fa-copy", - "enum": [ - "symlink", - "rellink", - "link", - "copy", - "copyNoFollow", - "move" - ], + "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"], "hidden": true }, "email_on_fail": { diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index ab1fa3a1..48b205af 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -43,6 +43,10 @@ workflow SCRNASEQ { ch_barcode_whitelist = [] } + // samplesheet - this is passed to the MTX conversion functions to add metadata to the + // AnnData objects. + ch_input = file(params.input) + //kallisto params ch_kallisto_index = params.kallisto_index ? file(params.kallisto_index) : [] kb_workflow = params.kb_workflow @@ -167,17 +171,17 @@ workflow SCRNASEQ { ch_mtx_matrices = ch_mtx_matrices.mix(CELLRANGERARC_ALIGN.out.cellranger_arc_out) } - // TODO - // // Run mtx to h5ad conversion subworkflow - // MTX_CONVERSION ( - // ch_mtx_matrices, - // ch_input, - // ch_txp2gene, - // ch_star_index - // ) - - // //Add Versions from MTX Conversion workflow too - // ch_versions.mix(MTX_CONVERSION.out.ch_versions) + TODO + // Run mtx to h5ad conversion subworkflow + MTX_CONVERSION ( + ch_mtx_matrices, + ch_input, + ch_txp2gene, + ch_star_index + ) + + //Add Versions from MTX Conversion workflow too + ch_versions.mix(MTX_CONVERSION.out.ch_versions) // // MODULE: MultiQC From 66bbb99ca71929effcb7062d66e92d6b55f84d30 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 10:24:09 +0100 Subject: [PATCH 37/49] Fix CI --- .github/workflows/ci.yml | 4 ---- 1 file changed, 4 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 746f26a2..b5524e7d 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -47,10 +47,6 @@ jobs: with: version: "${{ matrix.NXF_VER }}" - - name: Run pipeline with test data - # TODO nf-core: You can customise CI pipeline run tests as required - # For example: adding multiple test runs with different parameters - # Remember that you can parallelise this by using strategy.matrix - name: Cache nf-test installation id: cache-software uses: actions/cache@v3 From 4203d1424d7c87a3ee8d1e179f474eae0aff9e87 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 10:28:04 +0100 Subject: [PATCH 38/49] Update modules and fix linting --- lib/{WorkflowScrnaseq.groovy => Utils.groovy} | 0 modules.json | 7 +- modules/nf-core/cellranger/count/main.nf | 2 +- modules/nf-core/cellranger/count/meta.yml | 3 +- .../count/templates/cellranger_count.py | 2 +- .../cellranger/count/tests/main.nf.test | 101 ++++++++++++++++++ .../cellranger/count/tests/main.nf.test.snap | 63 +++++++++++ .../cellranger/count/tests/nextflow.config | 24 +++++ .../nf-core/cellranger/count/tests/tags.yml | 2 + workflows/scrnaseq.nf | 2 +- 10 files changed, 196 insertions(+), 10 deletions(-) rename lib/{WorkflowScrnaseq.groovy => Utils.groovy} (100%) create mode 100644 modules/nf-core/cellranger/count/tests/main.nf.test create mode 100644 modules/nf-core/cellranger/count/tests/main.nf.test.snap create mode 100644 modules/nf-core/cellranger/count/tests/nextflow.config create mode 100644 modules/nf-core/cellranger/count/tests/tags.yml diff --git a/lib/WorkflowScrnaseq.groovy b/lib/Utils.groovy similarity index 100% rename from lib/WorkflowScrnaseq.groovy rename to lib/Utils.groovy diff --git a/modules.json b/modules.json index e1234f4c..805606f5 100644 --- a/modules.json +++ b/modules.json @@ -7,7 +7,7 @@ "nf-core": { "cellranger/count": { "branch": "master", - "git_sha": "575e1bc54b083fb15e7dd8b5fcc40bea60e8ce83", + "git_sha": "a2dfd9a0b2e192243695711c723d652959de39fc", "installed_by": ["modules"] }, "cellranger/mkgtf": { @@ -35,11 +35,6 @@ "git_sha": "4196b1b2e7ce265892f3979eabf7a9ddc030702f", "installed_by": ["modules"] }, - "custom/dumpsoftwareversions": { - "branch": "master", - "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93", - "installed_by": ["modules"] - }, "fastqc": { "branch": "master", "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c", diff --git a/modules/nf-core/cellranger/count/main.nf b/modules/nf-core/cellranger/count/main.nf index d7a191fc..42aa09c9 100644 --- a/modules/nf-core/cellranger/count/main.nf +++ b/modules/nf-core/cellranger/count/main.nf @@ -32,7 +32,7 @@ process CELLRANGER_COUNT { def prefix = task.ext.prefix ?: "${meta.id}" """ mkdir -p "${prefix}/outs/" - touch ${prefix}/outs/fake_file.txt + echo "$prefix" > ${prefix}/outs/fake_file.txt cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/cellranger/count/meta.yml b/modules/nf-core/cellranger/count/meta.yml index c1f4259a..1f1768a8 100644 --- a/modules/nf-core/cellranger/count/meta.yml +++ b/modules/nf-core/cellranger/count/meta.yml @@ -10,7 +10,8 @@ tools: homepage: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/what-is-cell-ranger documentation: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/tutorial_ov tool_dev_url: https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/tutorial_ov - licence: 10x Genomics EULA + licence: + - 10x Genomics EULA input: - meta: type: map diff --git a/modules/nf-core/cellranger/count/templates/cellranger_count.py b/modules/nf-core/cellranger/count/templates/cellranger_count.py index 1527ba76..53360f23 100644 --- a/modules/nf-core/cellranger/count/templates/cellranger_count.py +++ b/modules/nf-core/cellranger/count/templates/cellranger_count.py @@ -36,7 +36,7 @@ def chunk_iter(seq, size): # do not match "SRR12345", "file_INFIXR12", etc filename_pattern = r'([^a-zA-Z0-9])R1([^a-zA-Z0-9])' -for i, (r1, r2) in enumerate(chunk_iter(fastqs, 2)): +for i, (r1, r2) in enumerate(chunk_iter(fastqs, 2), start=1): # double escapes are required because nextflow processes this python 'template' if re.sub(filename_pattern, r'\\1R2\\2', r1.name) != r2.name: raise AssertionError( diff --git a/modules/nf-core/cellranger/count/tests/main.nf.test b/modules/nf-core/cellranger/count/tests/main.nf.test new file mode 100644 index 00000000..c779b89e --- /dev/null +++ b/modules/nf-core/cellranger/count/tests/main.nf.test @@ -0,0 +1,101 @@ +nextflow_process { + + name "Test Process CELLRANGER_COUNT" + script "../main.nf" + process "CELLRANGER_COUNT" + + tag "modules" + tag "modules_nfcore" + tag "cellranger" + tag "cellranger/count" + tag "cellranger/mkref" + tag "cellranger/mkgtf" + + setup { + config "./nextflow.config" + + run("CELLRANGER_MKGTF") { + script "../../mkgtf/main.nf" + process { + """ + input[0] = file(params.test_data['homo_sapiens']['genome']['genome_gtf'], checkIfExists: true) + """ + } + } + run("CELLRANGER_MKREF") { + script "../../mkref/main.nf" + process { + """ + input[0] = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true) + input[1] = CELLRANGER_MKGTF.out.gtf + input[2] = "homo_sapiens_chr22_reference" + """ + } + } + } + + test("10x example file") { + config "./nextflow.config" + when { + process { + """ + input[0] = [ + [ id:'test_10x', single_end:false, strandedness:'auto' ], // meta map + [ + file(params.test_data['homo_sapiens']['10xgenomics']['cellranger']['test_10x_5k_cmvpos_tcells_gex1_fastq_1_gz'], checkIfExists: true), + file(params.test_data['homo_sapiens']['10xgenomics']['cellranger']['test_10x_5k_cmvpos_tcells_gex1_fastq_2_gz'], checkIfExists: true) + ] + ] + input[1] = CELLRANGER_MKREF.out.reference + """ + } + } + + then { + assertAll( + { assert process.success }, + { + assert snapshot( + process.out.versions, + process.out.outs[0][1].findAll { file(it).name !in [ + 'web_summary.html', // unstable checksum + 'barcodes.tsv.gz' // empty file in test data -> would raise linting error + ]} + ).match() + }, + { assert file(process.out.outs.get(0).get(1).find { file(it).name == 'web_summary.html' }).exists() }, + { assert file(process.out.outs.get(0).get(1).find { file(it).name == 'barcodes.tsv.gz' }).exists() } + ) + } + + } + + test("10x example file - stub") { + + options "-stub" + + when { + process { + """ + input[0] = [ + [ id:'test_10x', single_end:false, strandedness:'auto' ], // meta map + [ + file(params.test_data['homo_sapiens']['10xgenomics']['cellranger']['test_10x_5k_cmvpos_tcells_gex1_fastq_1_gz'], checkIfExists: true), + file(params.test_data['homo_sapiens']['10xgenomics']['cellranger']['test_10x_5k_cmvpos_tcells_gex1_fastq_2_gz'], checkIfExists: true) + ] + ] + input[1] = CELLRANGER_MKREF.out.reference + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + +} diff --git a/modules/nf-core/cellranger/count/tests/main.nf.test.snap b/modules/nf-core/cellranger/count/tests/main.nf.test.snap new file mode 100644 index 00000000..7eafafd0 --- /dev/null +++ b/modules/nf-core/cellranger/count/tests/main.nf.test.snap @@ -0,0 +1,63 @@ +{ + "10x example file": { + "content": [ + [ + "versions.yml:md5,ec6a0c18d2a8332e42956d07215a657c" + ], + [ + "filtered_feature_bc_matrix.h5:md5,cd440a402b661dc307356057d0dd3348", + "features.tsv.gz:md5,9f93621be0bede2b75596ad255607633", + "matrix.mtx.gz:md5,1736b88199c1dd71e907f9b93becc4f8", + "metrics_summary.csv:md5,c295fe3ccbb6ce118482964ca9c748d4", + "molecule_info.h5:md5,6204ac0b164b6e06e65954d072afe599", + "possorted_genome_bam.bam:md5,32fe604968326d98e8c0c36ce3c5ee8d", + "possorted_genome_bam.bam.bai:md5,e37e792ca1b528e64cd57f7d70dae3ed", + "raw_feature_bc_matrix.h5:md5,8521dbdf077e029ae35e682d746eb79d", + "features.tsv.gz:md5,9f93621be0bede2b75596ad255607633", + "matrix.mtx.gz:md5,6294c0359b29a86ba7b06e07d4b8a134" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-03-06T09:30:22.104987533" + }, + "10x example file - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test_10x", + "single_end": false, + "strandedness": "auto" + }, + "fake_file.txt:md5,0d98223c768861fd6af96f00148dbb8d" + ] + ], + "1": [ + "versions.yml:md5,30cee1a9146b01c48d9b1db6bbe813b6" + ], + "outs": [ + [ + { + "id": "test_10x", + "single_end": false, + "strandedness": "auto" + }, + "fake_file.txt:md5,0d98223c768861fd6af96f00148dbb8d" + ] + ], + "versions": [ + "versions.yml:md5,30cee1a9146b01c48d9b1db6bbe813b6" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "23.10.1" + }, + "timestamp": "2024-03-05T17:16:12.322822411" + } +} \ No newline at end of file diff --git a/modules/nf-core/cellranger/count/tests/nextflow.config b/modules/nf-core/cellranger/count/tests/nextflow.config new file mode 100644 index 00000000..2859b34a --- /dev/null +++ b/modules/nf-core/cellranger/count/tests/nextflow.config @@ -0,0 +1,24 @@ +process { + withName: CELLRANGER_MKGTF { + ext.args = '--attribute=gene_biotype:protein_coding \ + --attribute=gene_biotype:lincRNA \ + --attribute=gene_biotype:antisense \ + --attribute=gene_biotype:IG_LV_gene \ + --attribute=gene_biotype:IG_V_gene \ + --attribute=gene_biotype:IG_V_pseudogene \ + --attribute=gene_biotype:IG_D_gene \ + --attribute=gene_biotype:IG_J_gene \ + --attribute=gene_biotype:IG_J_pseudogene \ + --attribute=gene_biotype:IG_C_gene \ + --attribute=gene_biotype:IG_C_pseudogene \ + --attribute=gene_biotype:TR_V_gene \ + --attribute=gene_biotype:TR_V_pseudogene \ + --attribute=gene_biotype:TR_D_gene \ + --attribute=gene_biotype:TR_J_gene \ + --attribute=gene_biotype:TR_J_pseudogene \ + --attribute=gene_biotype:TR_C_gene' + } + withName: CELLRANGER_COUNT { + ext.args = '--chemistry SC3Pv3' + } +} diff --git a/modules/nf-core/cellranger/count/tests/tags.yml b/modules/nf-core/cellranger/count/tests/tags.yml new file mode 100644 index 00000000..a29a7044 --- /dev/null +++ b/modules/nf-core/cellranger/count/tests/tags.yml @@ -0,0 +1,2 @@ +cellranger/count: + - "modules/nf-core/cellranger/count/**" diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index 48b205af..e1db493a 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -22,7 +22,7 @@ workflow SCRNASEQ { main: - protocol_config = WorkflowScrnaseq.getProtocol(workflow, log, params.aligner, params.protocol) + protocol_config = Utils.getProtocol(workflow, log, params.aligner, params.protocol) if (protocol_config['protocol'] == 'auto' && params.aligner != "cellranger") { error "Only cellranger supports `protocol = 'auto'`. Please specify the protocol manually!" } From fcc405b6aec05948de2797b3bc1a52dd23e68f48 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 10:46:35 +0100 Subject: [PATCH 39/49] Fix multiqc --- workflows/scrnaseq.nf | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index e1db493a..d077c1f0 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -71,7 +71,7 @@ workflow SCRNASEQ { if (!params.skip_fastqc) { FASTQC_CHECK ( ch_fastq ) ch_versions = ch_versions.mix(FASTQC_CHECK.out.fastqc_version) - ch_multiqc_files = ch_multiqc_files.mix(FASTQC_CHECK.out.fastqc_zip) + ch_multiqc_files = ch_multiqc_files.mix(FASTQC_CHECK.out.fastqc_zip.map{ meta, it -> it }) } ch_filter_gtf = GTF_GENE_FILTER ( ch_genome_fasta, ch_gtf ).gtf @@ -171,7 +171,6 @@ workflow SCRNASEQ { ch_mtx_matrices = ch_mtx_matrices.mix(CELLRANGERARC_ALIGN.out.cellranger_arc_out) } - TODO // Run mtx to h5ad conversion subworkflow MTX_CONVERSION ( ch_mtx_matrices, From b6b80a9ae035402a325ff6cdcde265f8fb8abb6f Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 11:10:27 +0100 Subject: [PATCH 40/49] Fix nf-test --- .gitignore | 2 +- nextflow.config | 4 ++++ subworkflows/local/starsolo.nf | 4 ++-- tests/main_pipeline_alevin.test.snap | 10 +++++----- tests/main_pipeline_cellranger.test.snap | 10 +++++----- tests/main_pipeline_kallisto.test.snap | 10 +++++----- tests/main_pipeline_star.test.snap | 10 +++++----- workflows/scrnaseq.nf | 2 +- 8 files changed, 28 insertions(+), 24 deletions(-) diff --git a/.gitignore b/.gitignore index a9ba2c52..61b9470a 100644 --- a/.gitignore +++ b/.gitignore @@ -9,4 +9,4 @@ testing* log/ reports/ testme.sh -.nf-test/ +.nf-test* diff --git a/nextflow.config b/nextflow.config index 495a8414..bf24e8a9 100644 --- a/nextflow.config +++ b/nextflow.config @@ -95,6 +95,10 @@ params { validationShowHiddenParams = false validate_params = true + // TODO temporary workaround a warning + // not used anywhere and should not be necessary anymore after a nf-validation plugin update + monochromeLogs = null + } // Load base.config by default for all pipelines diff --git a/subworkflows/local/starsolo.nf b/subworkflows/local/starsolo.nf index 47b2e757..e6c95409 100644 --- a/subworkflows/local/starsolo.nf +++ b/subworkflows/local/starsolo.nf @@ -57,8 +57,8 @@ workflow STARSOLO { emit: ch_versions // get rid of meta for star index - star_index = star_index.map{ meta, index -> index} + star_index = star_index.map{ meta, index -> index } star_result = STAR_ALIGN.out.tab star_counts = STAR_ALIGN.out.counts - for_multiqc = STAR_ALIGN.out.log_final + for_multiqc = STAR_ALIGN.out.log_final.map{ meta, it -> it } } diff --git a/tests/main_pipeline_alevin.test.snap b/tests/main_pipeline_alevin.test.snap index 9d194012..1ea49820 100644 --- a/tests/main_pipeline_alevin.test.snap +++ b/tests/main_pipeline_alevin.test.snap @@ -3,19 +3,19 @@ "content": [ { "stderr": [ - + ], "errorReport": "", "exitStatus": 0, "failed": false, "stdout": [ - + ], "errorMessage": "", "trace": { "tasksFailed": 0, - "tasksCount": 16, - "tasksSucceeded": 16 + "tasksCount": 14, + "tasksSucceeded": 14 }, "name": "workflow", "success": true @@ -29,4 +29,4 @@ ], "timestamp": "2024-01-19T10:28:35.652763852" } -} \ No newline at end of file +} diff --git a/tests/main_pipeline_cellranger.test.snap b/tests/main_pipeline_cellranger.test.snap index 5f88b954..865d651b 100644 --- a/tests/main_pipeline_cellranger.test.snap +++ b/tests/main_pipeline_cellranger.test.snap @@ -3,19 +3,19 @@ "content": [ { "stderr": [ - + ], "errorReport": "", "exitStatus": 0, "failed": false, "stdout": [ - + ], "errorMessage": "", "trace": { "tasksFailed": 0, - "tasksCount": 15, - "tasksSucceeded": 15 + "tasksCount": 13, + "tasksSucceeded": 13 }, "name": "workflow", "success": true @@ -37,4 +37,4 @@ ], "timestamp": "2024-01-22T15:19:20.134275449" } -} \ No newline at end of file +} diff --git a/tests/main_pipeline_kallisto.test.snap b/tests/main_pipeline_kallisto.test.snap index b0fb50bb..e57b77af 100644 --- a/tests/main_pipeline_kallisto.test.snap +++ b/tests/main_pipeline_kallisto.test.snap @@ -3,19 +3,19 @@ "content": [ { "stderr": [ - + ], "errorReport": "", "exitStatus": 0, "failed": false, "stdout": [ - + ], "errorMessage": "", "trace": { "tasksFailed": 0, - "tasksCount": 14, - "tasksSucceeded": 14 + "tasksCount": 12, + "tasksSucceeded": 12 }, "name": "workflow", "success": true @@ -31,4 +31,4 @@ ], "timestamp": "2024-01-23T12:19:47.921508953" } -} \ No newline at end of file +} diff --git a/tests/main_pipeline_star.test.snap b/tests/main_pipeline_star.test.snap index ef086f60..eaa97b8b 100644 --- a/tests/main_pipeline_star.test.snap +++ b/tests/main_pipeline_star.test.snap @@ -3,19 +3,19 @@ "content": [ { "stderr": [ - + ], "errorReport": "", "exitStatus": 0, "failed": false, "stdout": [ - + ], "errorMessage": "", "trace": { "tasksFailed": 0, - "tasksCount": 14, - "tasksSucceeded": 14 + "tasksCount": 12, + "tasksSucceeded": 12 }, "name": "workflow", "success": true @@ -35,4 +35,4 @@ ], "timestamp": "2024-01-19T15:46:22.470527538" } -} \ No newline at end of file +} diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf index d077c1f0..f2a0ba3f 100644 --- a/workflows/scrnaseq.nf +++ b/workflows/scrnaseq.nf @@ -105,7 +105,7 @@ workflow SCRNASEQ { ch_fastq ) ch_versions = ch_versions.mix(SCRNASEQ_ALEVIN.out.ch_versions) - ch_multiqc_files = ch_multiqc_files.mix(SCRNASEQ_ALEVIN.out.alevin_results) + ch_multiqc_files = ch_multiqc_files.mix(SCRNASEQ_ALEVIN.out.alevin_results.map{ meta, it -> it }) ch_mtx_matrices = ch_mtx_matrices.mix(SCRNASEQ_ALEVIN.out.alevin_results) } From 273a157027ed924329dbc4fa6923ff761009c6fa Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 11:19:47 +0100 Subject: [PATCH 41/49] Fix nf-test --- tests/main_pipeline_alevin.test | 2 +- tests/main_pipeline_cellranger.test | 2 +- tests/main_pipeline_kallisto.test | 2 +- tests/main_pipeline_star.test | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tests/main_pipeline_alevin.test b/tests/main_pipeline_alevin.test index 303a625b..4bbd3cfb 100644 --- a/tests/main_pipeline_alevin.test +++ b/tests/main_pipeline_alevin.test @@ -30,7 +30,7 @@ nextflow_pipeline { {assert workflow.success}, // How many tasks were executed? - {assert workflow.trace.tasks().size() == 16}, + {assert workflow.trace.tasks().size() == 14}, // How many results were produced? {assert path("${outputDir}/results_alevin").list().size() == 5}, diff --git a/tests/main_pipeline_cellranger.test b/tests/main_pipeline_cellranger.test index 996c0f76..b7b34fa5 100644 --- a/tests/main_pipeline_cellranger.test +++ b/tests/main_pipeline_cellranger.test @@ -30,7 +30,7 @@ nextflow_pipeline { {assert workflow.success}, // How many tasks were executed? - {assert workflow.trace.tasks().size() == 15}, + {assert workflow.trace.tasks().size() == 13}, // How many results were produced? {assert path("${outputDir}/results_cellranger").list().size() == 4}, diff --git a/tests/main_pipeline_kallisto.test b/tests/main_pipeline_kallisto.test index 98ede8c4..ae6675b1 100644 --- a/tests/main_pipeline_kallisto.test +++ b/tests/main_pipeline_kallisto.test @@ -30,7 +30,7 @@ nextflow_pipeline { {assert workflow.success}, // How many tasks were executed? - {assert workflow.trace.tasks().size() == 14}, + {assert workflow.trace.tasks().size() == 12}, // How many results were produced? {assert path("${outputDir}/results_kallisto").list().size() == 4}, diff --git a/tests/main_pipeline_star.test b/tests/main_pipeline_star.test index 6616ea87..111c5243 100644 --- a/tests/main_pipeline_star.test +++ b/tests/main_pipeline_star.test @@ -30,7 +30,7 @@ nextflow_pipeline { {assert workflow.success}, // How many tasks were executed? - {assert workflow.trace.tasks().size() == 14}, + {assert workflow.trace.tasks().size() == 12}, // How many results were produced? {assert path("${outputDir}/results_star").list().size() == 4}, From 0c53b9b1c11cec848e3870730e549cc798da1fa6 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 11:34:27 +0100 Subject: [PATCH 42/49] Fix lint --- .nf-core.yml | 2 ++ modules.json | 2 +- modules/nf-core/multiqc/tests/main.nf.test.snap | 12 ++++++------ 3 files changed, 9 insertions(+), 7 deletions(-) diff --git a/.nf-core.yml b/.nf-core.yml index 738ad918..6a1c8178 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -3,3 +3,5 @@ lint: template_strings: False files_unchanged: - .github/ISSUE_TEMPLATE/bug_report.yml + files_exist: + - lib/Utils.groovy diff --git a/modules.json b/modules.json index 805606f5..8aa2641e 100644 --- a/modules.json +++ b/modules.json @@ -62,7 +62,7 @@ }, "multiqc": { "branch": "master", - "git_sha": "9e71d8519dfbfc328c078bba14d4bd4c99e39a94", + "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a", "installed_by": ["modules"] }, "star/genomegenerate": { diff --git a/modules/nf-core/multiqc/tests/main.nf.test.snap b/modules/nf-core/multiqc/tests/main.nf.test.snap index 549ba79c..bfebd802 100644 --- a/modules/nf-core/multiqc/tests/main.nf.test.snap +++ b/modules/nf-core/multiqc/tests/main.nf.test.snap @@ -2,14 +2,14 @@ "multiqc_versions_single": { "content": [ [ - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], "meta": { "nf-test": "0.8.4", "nextflow": "23.10.1" }, - "timestamp": "2024-01-31T17:43:40.529579" + "timestamp": "2024-02-29T08:48:55.657331" }, "multiqc_stub": { "content": [ @@ -17,25 +17,25 @@ "multiqc_report.html", "multiqc_data", "multiqc_plots", - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], "meta": { "nf-test": "0.8.4", "nextflow": "23.10.1" }, - "timestamp": "2024-01-31T17:45:09.605359" + "timestamp": "2024-02-29T08:49:49.071937" }, "multiqc_versions_config": { "content": [ [ - "versions.yml:md5,14e9a2661241abd828f4f06a7b5c222d" + "versions.yml:md5,21f35ee29416b9b3073c28733efe4b7d" ] ], "meta": { "nf-test": "0.8.4", "nextflow": "23.10.1" }, - "timestamp": "2024-01-31T17:44:53.535994" + "timestamp": "2024-02-29T08:49:25.457567" } } \ No newline at end of file From b7ad599a1527adffedd962f92ad1c9ba5d8db457 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 11:42:00 +0100 Subject: [PATCH 43/49] attempt ignore monochromeLogs lint --- .nf-core.yml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.nf-core.yml b/.nf-core.yml index 6a1c8178..6dc2a658 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -5,3 +5,5 @@ lint: - .github/ISSUE_TEMPLATE/bug_report.yml files_exist: - lib/Utils.groovy + schema_params: + - monochromeLogs From 58f5a54ed0b10ff8ecc8a2295a084d1720d94339 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 11:44:07 +0100 Subject: [PATCH 44/49] attempt ignore monochromeLogs lint --- .nf-core.yml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/.nf-core.yml b/.nf-core.yml index 6dc2a658..1f6d2308 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -5,5 +5,4 @@ lint: - .github/ISSUE_TEMPLATE/bug_report.yml files_exist: - lib/Utils.groovy - schema_params: - - monochromeLogs + schema_params: False From e87bfbf6687547476b97996bde56b0e827bdc2ab Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 11:46:27 +0100 Subject: [PATCH 45/49] Update comments --- .nf-core.yml | 2 ++ nextflow.config | 1 + 2 files changed, 3 insertions(+) diff --git a/.nf-core.yml b/.nf-core.yml index 1f6d2308..90cfd21c 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -5,4 +5,6 @@ lint: - .github/ISSUE_TEMPLATE/bug_report.yml files_exist: - lib/Utils.groovy + # TODO This is because of an issue with the monochromeLogs parameter + # See nextflow.config for details schema_params: False diff --git a/nextflow.config b/nextflow.config index bf24e8a9..3fe5c47f 100644 --- a/nextflow.config +++ b/nextflow.config @@ -97,6 +97,7 @@ params { // TODO temporary workaround a warning // not used anywhere and should not be necessary anymore after a nf-validation plugin update + // TODO when removing this, also remove the ignored lint check from .nf-core.yml monochromeLogs = null } From fdda7a596fc4dd733976540c05558c5efceda67d Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 12:39:28 +0100 Subject: [PATCH 46/49] Delete .nf-test.log --- .nf-test.log | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 .nf-test.log diff --git a/.nf-test.log b/.nf-test.log deleted file mode 100644 index ca137888..00000000 --- a/.nf-test.log +++ /dev/null @@ -1,17 +0,0 @@ -Feb-27 21:54:16.881 [main] INFO com.askimed.nf.test.App - nf-test 0.8.4 -Feb-27 21:54:16.895 [main] INFO com.askimed.nf.test.App - Arguments: [test, tests/main_pipeline_kallisto.test, --update-snapshot] -Feb-27 21:54:17.590 [main] INFO com.askimed.nf.test.App - Nextflow Version: 23.10.1 -Feb-27 21:54:17.592 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Load config from file /home/ec2-user/scrnaseq/nf-test.config... -Feb-27 21:54:17.887 [main] INFO com.askimed.nf.test.commands.RunTestsCommand - Detected 1 test files. -Feb-27 21:54:18.162 [main] INFO com.askimed.nf.test.config.FileStaging - Copy directory '/home/ec2-user/scrnaseq/bin' to '/home/ec2-user/scrnaseq/.nf-test/tests/72e0d0f6b834ab79755c0f97ef8c4ca8/meta/bin' -Feb-27 21:54:18.164 [main] INFO com.askimed.nf.test.config.FileStaging - Copy directory '/home/ec2-user/scrnaseq/lib' to '/home/ec2-user/scrnaseq/.nf-test/tests/72e0d0f6b834ab79755c0f97ef8c4ca8/meta/lib' -Feb-27 21:54:18.164 [main] INFO com.askimed.nf.test.config.FileStaging - Copy directory '/home/ec2-user/scrnaseq/assets' to '/home/ec2-user/scrnaseq/.nf-test/tests/72e0d0f6b834ab79755c0f97ef8c4ca8/meta/assets' -Feb-27 21:54:18.171 [main] DEBUG com.askimed.nf.test.core.AbstractTest - Stage 0 user provided files... -Feb-27 21:54:18.174 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Started test plan -Feb-27 21:54:18.174 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Running testsuite 'Test Workflow main.nf' from file '/home/ec2-user/scrnaseq/tests/main_pipeline_kallisto.test'. -Feb-27 21:54:18.174 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Run test '72e0d0f6: test-dataset_kallisto_aligner'. type: com.askimed.nf.test.lang.pipeline.PipelineTest -Feb-27 21:55:36.281 [main] DEBUG com.askimed.nf.test.lang.extensions.SnapshotFile - Load snapshots from file '/home/ec2-user/scrnaseq/tests/main_pipeline_kallisto.test.snap' -Feb-27 21:55:36.305 [main] DEBUG com.askimed.nf.test.lang.extensions.Snapshot - Snapshots 'test-dataset_kallisto_aligner' match. -Feb-27 21:55:36.306 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Test '72e0d0f6: test-dataset_kallisto_aligner' finished. status: PASSED -Feb-27 21:55:36.308 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Testsuite 'Test Workflow main.nf' finished. snapshot file: true, skipped tests: false, failed tests: false -Feb-27 21:55:36.308 [main] INFO com.askimed.nf.test.core.TestExecutionEngine - Executed 1 tests. 0 tests failed. Done! From 6b46540896052f43db7e91b5c4d6e95f85498013 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 12:40:45 +0100 Subject: [PATCH 47/49] Update nextflow_schema.json --- nextflow_schema.json | 1 - 1 file changed, 1 deletion(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 0f1433c4..42599d59 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -237,7 +237,6 @@ "type": "string", "description": "Specify a path to the intron transcripts-to-capture.", "fa_icon": "fas fa-rainbow" - "fa_icon": "fas fa-fish", "format": "file-path", "exists": true }, From 904743e1f1e2ed62485f10135925ad33d6b306c3 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 12:46:52 +0100 Subject: [PATCH 48/49] Fix nextflow schema --- nextflow_schema.json | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/nextflow_schema.json b/nextflow_schema.json index 42599d59..65b56954 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -224,7 +224,9 @@ "kallisto_index": { "type": "string", "description": "Specify a path to the precomputed Kallisto index.", - "fa_icon": "fas fa-rainbow" + "fa_icon": "fas fa-rainbow", + "format": "file-path", + "exists": true }, "kb_t1c": { "type": "string", @@ -236,7 +238,7 @@ "kb_t2c": { "type": "string", "description": "Specify a path to the intron transcripts-to-capture.", - "fa_icon": "fas fa-rainbow" + "fa_icon": "fas fa-rainbow", "format": "file-path", "exists": true }, From 600619f7eeff522b36523630dc6c60a1c0fd6227 Mon Sep 17 00:00:00 2001 From: Gregor Sturm Date: Thu, 7 Mar 2024 12:50:46 +0100 Subject: [PATCH 49/49] Update changelog --- CHANGELOG.md | 4 +++- nextflow_schema.json | 5 ----- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index b42791db..a9d9a7e7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,7 +5,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## v2.6.0dev - [date] -- [[#91](https://github.com/nf-core/scrnaseq/issues/91)] - Change from pytests to nf-test +- Change from pytests to nf-test ([#291](https://github.com/nf-core/scrnaseq/pull/291)) +- Update template to v2.13.1 ([#309](https://github.com/nf-core/scrnaseq/pull/309)) +- Update to kallisto|bustools v0.28.2 ([#294](https://github.com/nf-core/scrnaseq/pull/294)) ## v2.5.1 diff --git a/nextflow_schema.json b/nextflow_schema.json index 65b56954..23f6e9b5 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -145,11 +145,6 @@ "default": "s3://ngi-igenomes/igenomes/", "fa_icon": "fas fa-cloud-download-alt", "hidden": true - }, - "txp2gene": { - "type": "string", - "description": "Kallisto or Alevin gene mapping file.", - "fa_icon": "fas map-marked-alt" } } },
    Process Name \\", - " \\ Software Version
    CUSTOM_DUMPSOFTWAREVERSIONSpython3.11.7
    yaml5.4.1
    TOOL1tool10.11.9
    TOOL2tool21.9
    WorkflowNextflow
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls
    File typeConventional base calls