diff --git a/CHANGELOG.md b/CHANGELOG.md index e276535..34b2665 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,7 +3,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## v2.3.0 - Oesterberg - 2024-02-14 +## v2.3.0 - Oesterberg - 2024-02-20 ### `Changed` diff --git a/assets/schema_input.json b/assets/schema_input.json index c0728a6..b15dc42 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -45,7 +45,7 @@ "filename": { "type": "string", "pattern": "^\\S+\\.(vcf|vcf.gz|tsv|fasta|fa)$", - "errorMessage": "Variants/proteins/peptides for sample must be provided and have one of the following extensions: '.vcf', '.vcf.gz', '.tsv', '.fasta', '.fa'" + "errorMessage": "Variants/proteins/peptides of a sample must be provided and have one of the following extensions: '.vcf', '.vcf.gz', '.tsv', '.fasta', '.fa'" } }, "required": ["sample", "alleles", "mhc_class", "filename"] diff --git a/bin/check_requested_models.py b/bin/check_requested_models.py index 3a4a63b..845666d 100755 --- a/bin/check_requested_models.py +++ b/bin/check_requested_models.py @@ -74,12 +74,7 @@ def __main__(): } # get the alleles - if args.alleles.startswith("http"): - alleles = [Allele(a) for a in urllib.request.urlopen(args.alleles).read().decode("utf-8").splitlines()] - elif args.alleles.endswith(".txt"): - alleles = [Allele(a) for a in open(args.alleles).read().splitlines()] - else: - alleles = [Allele(a) for a in args.alleles.split(";")] + alleles = [Allele(a) for a in args.alleles.split(";")] peptide_lengths = [] if args.peptides: diff --git a/docs/usage.md b/docs/usage.md index 5c62037..ece95e6 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -23,8 +23,7 @@ The pipeline currently accepts three different types of input that are genomic v The supported file formats for genomic variants are `.vcf`, `.vcf.gz` and `tsv`. > [!IMPORTANT] -> Please note that genomic variants have to be annotated. Currently, we support variants that have been annotated using [SnpEff](http://pcingola.> github.io/SnpEff/). -> Support for [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html) will be available with one of the upcoming versions. +> Please note that genomic variants have to be annotated. Currently, we support variants that have been annotated using [SnpEff](http://pcingola.> github.io/SnpEff/) and [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html). `tsv` files with genomic variants have to provide the following columns: @@ -36,7 +35,7 @@ chr1 12954870 12954870 C T . 0 NORMAL:414,TUMOR:8 . missense_variant 0.5 transcr ``` -For genomic variants, reference information from `Ensembl BioMart` is used. The default database version is the most recent `GRCh37` version. If you want to do the predictions based on `GRCh38` as the reference genome, please specify `--genome_reference grch37` in your pipeline call. +For genomic variants, reference information from `Ensembl BioMart` is used. The default database version is the most recent `GRCh37` version. If you want to do the predictions based on `GRCh38` as the reference genome, please specify `--genome_reference grch38` in your pipeline call. You can also specify valid `Ensembl BioMart` archive version urls as `--genome_reference` value, e.g. [the archive version of December 2021](http://dec2021.archive.ensembl.org/). diff --git a/lib/WorkflowEpitopeprediction.groovy b/lib/WorkflowEpitopeprediction.groovy index 94179f7..5f54640 100755 --- a/lib/WorkflowEpitopeprediction.groovy +++ b/lib/WorkflowEpitopeprediction.groovy @@ -54,7 +54,6 @@ class WorkflowEpitopeprediction { // 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() @@ -68,7 +67,6 @@ class WorkflowEpitopeprediction { // 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() diff --git a/modules/nf-core/fastqc/environment.yml b/modules/nf-core/fastqc/environment.yml deleted file mode 100644 index 1787b38..0000000 --- a/modules/nf-core/fastqc/environment.yml +++ /dev/null @@ -1,7 +0,0 @@ -name: fastqc -channels: - - conda-forge - - bioconda - - defaults -dependencies: - - bioconda::fastqc=0.12.1 diff --git a/modules/nf-core/fastqc/tests/main.nf.test b/modules/nf-core/fastqc/tests/main.nf.test deleted file mode 100644 index 1f21c66..0000000 --- a/modules/nf-core/fastqc/tests/main.nf.test +++ /dev/null @@ -1,212 +0,0 @@ -nextflow_process { - - name "Test Process FASTQC" - script "../main.nf" - process "FASTQC" - - tag "modules" - tag "modules_nfcore" - tag "fastqc" - - test("sarscov2 single-end [fastq]") { - - when { - process { - """ - input[0] = Channel.of([ - [ id: 'test', single_end:true ], - [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true) ] - ]) - """ - } - } - - then { - assertAll ( - { assert process.success }, - - // NOTE The report contains the date inside it, which means that the md5sum is stable per day, but not longer than that. So you can't md5sum it. - // looks like this:
    Mon 2 Oct 2023
    test.gz
    - // https://github.com/nf-core/modules/pull/3903#issuecomment-1743620039 - - { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" }, - { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, - { assert path(process.out.html[0][1]).text.contains("File typeConventional base calls") }, - - { assert snapshot(process.out.versions).match("versions") } - ) - } - } - - test("sarscov2 paired-end [fastq]") { - - when { - process { - """ - input[0] = Channel.of([ - [id: 'test', single_end: false], // meta map - [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true), - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true) ] - ]) - """ - } - } - - then { - assertAll ( - { assert process.success }, - - { assert process.out.html[0][1][0] ==~ ".*/test_1_fastqc.html" }, - { assert process.out.html[0][1][1] ==~ ".*/test_2_fastqc.html" }, - { assert process.out.zip[0][1][0] ==~ ".*/test_1_fastqc.zip" }, - { assert process.out.zip[0][1][1] ==~ ".*/test_2_fastqc.zip" }, - { assert path(process.out.html[0][1][0]).text.contains("File typeConventional base calls") }, - { assert path(process.out.html[0][1][1]).text.contains("File typeConventional base calls") }, - - { assert snapshot(process.out.versions).match("versions") } - ) - } - } - - test("sarscov2 interleaved [fastq]") { - - when { - process { - """ - input[0] = Channel.of([ - [id: 'test', single_end: false], // meta map - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_interleaved.fastq.gz', checkIfExists: true) - ]) - """ - } - } - - then { - assertAll ( - { assert process.success }, - - { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" }, - { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, - { assert path(process.out.html[0][1]).text.contains("File typeConventional base calls") }, - - { assert snapshot(process.out.versions).match("versions") } - ) - } - } - - test("sarscov2 paired-end [bam]") { - - when { - process { - """ - input[0] = Channel.of([ - [id: 'test', single_end: false], // meta map - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true) - ]) - """ - } - } - - then { - assertAll ( - { assert process.success }, - - { assert process.out.html[0][1] ==~ ".*/test_fastqc.html" }, - { assert process.out.zip[0][1] ==~ ".*/test_fastqc.zip" }, - { assert path(process.out.html[0][1]).text.contains("File typeConventional base calls") }, - - { assert snapshot(process.out.versions).match("versions") } - ) - } - } - - test("sarscov2 multiple [fastq]") { - - when { - process { - """ - input[0] = Channel.of([ - [id: 'test', single_end: false], // meta map - [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true), - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true), - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test2_1.fastq.gz', checkIfExists: true), - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test2_2.fastq.gz', checkIfExists: true) ] - ]) - """ - } - } - - then { - assertAll ( - { assert process.success }, - - { assert process.out.html[0][1][0] ==~ ".*/test_1_fastqc.html" }, - { assert process.out.html[0][1][1] ==~ ".*/test_2_fastqc.html" }, - { assert process.out.html[0][1][2] ==~ ".*/test_3_fastqc.html" }, - { assert process.out.html[0][1][3] ==~ ".*/test_4_fastqc.html" }, - { assert process.out.zip[0][1][0] ==~ ".*/test_1_fastqc.zip" }, - { assert process.out.zip[0][1][1] ==~ ".*/test_2_fastqc.zip" }, - { assert process.out.zip[0][1][2] ==~ ".*/test_3_fastqc.zip" }, - { assert process.out.zip[0][1][3] ==~ ".*/test_4_fastqc.zip" }, - { assert path(process.out.html[0][1][0]).text.contains("File typeConventional base calls") }, - { assert path(process.out.html[0][1][1]).text.contains("File typeConventional base calls") }, - { assert path(process.out.html[0][1][2]).text.contains("File typeConventional base calls") }, - { assert path(process.out.html[0][1][3]).text.contains("File typeConventional base calls") }, - - { assert snapshot(process.out.versions).match("versions") } - ) - } - } - - test("sarscov2 custom_prefix") { - - when { - process { - """ - input[0] = Channel.of([ - [ id:'mysample', single_end:true ], // meta map - file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true) - ]) - """ - } - } - - then { - assertAll ( - { assert process.success }, - - { assert process.out.html[0][1] ==~ ".*/mysample_fastqc.html" }, - { assert process.out.zip[0][1] ==~ ".*/mysample_fastqc.zip" }, - { assert path(process.out.html[0][1]).text.contains("File typeConventional base calls") }, - - { assert snapshot(process.out.versions).match("versions") } - ) - } - } - - test("sarscov2 single-end [fastq] - stub") { - - options "-stub" - - when { - process { - """ - input[0] = Channel.of([ - [ id: 'test', single_end:true ], - [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true) ] - ]) - """ - } - } - - then { - assertAll ( - { 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() } - ) - } - } - -} diff --git a/modules/nf-core/fastqc/tests/main.nf.test.snap b/modules/nf-core/fastqc/tests/main.nf.test.snap deleted file mode 100644 index 5d624bb..0000000 --- a/modules/nf-core/fastqc/tests/main.nf.test.snap +++ /dev/null @@ -1,20 +0,0 @@ -{ - "sarscov2 single-end [fastq] - stub": { - "content": [ - [ - "test.html", - "test.zip", - "versions.yml:md5,e1cc25ca8af856014824abd842e93978" - ] - ], - "timestamp": "2024-01-17T18:40:57.254299" - }, - "versions": { - "content": [ - [ - "versions.yml:md5,e1cc25ca8af856014824abd842e93978" - ] - ], - "timestamp": "2024-01-17T18:36:50.033627" - } -} \ No newline at end of file diff --git a/modules/nf-core/fastqc/tests/tags.yml b/modules/nf-core/fastqc/tests/tags.yml deleted file mode 100644 index 7834294..0000000 --- a/modules/nf-core/fastqc/tests/tags.yml +++ /dev/null @@ -1,2 +0,0 @@ -fastqc: - - modules/nf-core/fastqc/**