diff --git a/CHANGELOG.md b/CHANGELOG.md index 9effe74f..4ad62ac3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -23,6 +23,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0. - [#150](https://github.com/nf-core/airrflow/pull/150): Fixed cprimer start position, when cprimer in R2 reads. - Remove need for a plot when Hamming threshold cannot be generated. - The shazam threshold process is not executed when the hamming threshold is provided. +- [#164](https://github.com/nf-core/airrflow/pull/150): Fixed AWS tests when running on fusion mounts, solving [#137](https://github.com/nf-core/airrflow/issues/137). ### `Dependencies` diff --git a/assets/references.bibtex b/assets/references.bibtex deleted file mode 100644 index b3133147..00000000 --- a/assets/references.bibtex +++ /dev/null @@ -1,74 +0,0 @@ -@article{ewels2016, - title={MultiQC: summarize analysis results for multiple tools and samples in a single report}, - author={Ewels, Philip and Magnusson, M{\aa}ns and Lundin, Sverker and K{\"a}ller, Max}, - journal={Bioinformatics}, - volume={32}, - number={19}, - pages={3047--3048}, - year={2016}, - publisher={Oxford University Press} -} -@article{VanderHeiden2014, - title={pRESTO: a toolkit for processing high-throughput sequencing raw reads of lymphocyte receptor repertoires}, - volume={30}, - ISSN={1460-2059}, - DOI={10.1093/bioinformatics/btu138}, - note={Citation Key: VanderHeiden2014}, number={13}, journal={Bioinformatics}, - publisher={Narnia}, - author={Vander Heiden, Jason A. and Yaari, Gur and Uduman, Mohamed and Stern, Joel N.H. and O’Connor, Kevin C. and Hafler, David A. and Vigneault, Francois and Kleinstein, Steven H.}, - year={2014}, - month={Jul}, - pages={1930–1932} -} -@article{Gupta2015, - title={Change-O: a toolkit for analyzing large-scale B cell immunoglobulin repertoire sequencing data.}, - volume={31}, - ISSN={1367-4803}, - DOI={10.1093/bioinformatics/btv359}, - note={Citation Key: Gupta2015}, - number={20}, - journal={Bioinformatics}, - publisher={Oxford University Press}, - author={Gupta, Namita T. and Vander Heiden, Jason A. and Uduman, Mohamed and Gadala-Maria, Daniel and Yaari, Gur and Kleinstein, Steven H.}, - year={2015}, - month={Oct}, - pages={3356–3358} -} -@article{Stern2014, - title={B cells populating the multiple sclerosis brain mature in the draining cervical lymph nodes}, - volume={6}, ISSN={19466242}, url={https://pubmed.ncbi.nlm.nih.gov/25100741/}, - DOI={10.1126/scitranslmed.3008879}, - number={248}, - journal={Science Translational Medicine}, - publisher={American Association for the Advancement of Science}, - author={Stern, Joel N.H. and Yaari, Gur and Vander Heiden, Jason A. and Church, George and Donahue, William F. and Hintzen, Rogier Q. and Huttner, Anita J. and Laman, Jon D. and Nagra, Rashed M. and Nylander, Alyssa and et al.}, - year={2014}, - month={Aug} -} -@article{Gadala-Maria2015, - title={Automated analysis of high-throughput B-cell sequencing data reveals a high frequency of novel immunoglobulin V gene segment alleles}, - volume={112}, - ISSN={1091-6490}, - DOI={10.1073/pnas.1417683112}, - number={8}, - journal={Proceedings of the National Academy of Sciences of the United States of America}, - author={Gadala-Maria, Daniel and Yaari, Gur and Uduman, Mohamed and Kleinstein, Steven H.}, - year={2015}, - month={Feb}, - pages={E862-870} -} -@misc{andrews2010, - title={FastQC: a quality control tool for high throughput sequence data}, - author={Andrews, Simon and others}, - year={2010} -} -@article{ewels2020, - title={The nf-core framework for community-curated bioinformatics pipelines}, - volume={38}, ISSN={15461696}, DOI={10.1038/s41587-020-0439-x}, - number={3}, journal={Nature Biotechnology}, - publisher={Nature Research}, - author={Ewels, Philip A. and Peltzer, Alexander and Fillinger, Sven and Patel, Harshil and Alneberg, Johannes and Wilm, Andreas and Garcia, Maxime Ulysse and Di Tommaso, Paolo and Nahnsen, Sven}, - year={2020}, - month={Mar}, - pages={276–278} -} diff --git a/assets/repertoire_comparison.Rmd b/assets/repertoire_comparison.Rmd index f0d56be6..d279f0c9 100644 --- a/assets/repertoire_comparison.Rmd +++ b/assets/repertoire_comparison.Rmd @@ -12,7 +12,6 @@ output: pdf_document: true html_notebook: toc: yes -bibliography: ./references.bibtex --- @@ -497,13 +496,53 @@ write.table(family, file = paste0(vfamily_dir, "/V_gene_distribution_by_sequence If you use nf-core/airrflow for your analysis, please cite it using the following DOI: [10.5281/zenodo.3607408](https://doi.org/10.5281/zenodo.3607408) -Please also cite the `nf-core` publication [@ewels2020]. +Please also cite the `nf-core` and `Nextflow` publications: + +- [nf-core](https://pubmed.ncbi.nlm.nih.gov/32055031/) + + > Ewels PA, Peltzer A, Fillinger S, Patel H, Alneberg J, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. The nf-core framework for community-curated bioinformatics pipelines. Nat Biotechnol. 2020 Mar;38(3):276-278. doi: 10.1038/s41587-020-0439-x. PubMed PMID: 32055031. + +- [Nextflow](https://pubmed.ncbi.nlm.nih.gov/28398311/) + + > Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C. Nextflow enables reproducible computational workflows. Nat Biotechnol. 2017 Apr 11;35(4):316-319. doi: 10.1038/nbt.3820. PubMed PMID: 28398311. In addition, citations for the tools and data used in this pipeline are as follows: -* **pRESTO** [@VanderHeiden2014] -* **SHazaM, Change-O** [@Gupta2015] -* **Alakazam** [@Stern2014] -* **TIgGER** [@Gadala-Maria2015] -* **FastQC** [@andrews2010] -* **MultiQC** [@ewels2016] +- [pRESTO](https://doi.org/10.1093/bioinformatics/btu138) + + > Vander Heiden, J. A., Yaari, G., Uduman, M., Stern, J. N. H., O’Connor, K. C., Hafler, D. A., … Kleinstein, S. H. (2014). pRESTO: a toolkit for processing high-throughput sequencing raw reads of lymphocyte receptor repertoires. Bioinformatics, 30(13), 1930–1932. + +- [SHazaM, Change-O](https://doi.org/10.1093/bioinformatics/btv359) + + > Gupta, N. T., Vander Heiden, J. A., Uduman, M., Gadala-Maria, D., Yaari, G., & Kleinstein, S. H. (2015). Change-O: a toolkit for analyzing large-scale B cell immunoglobulin repertoire sequencing data: Table 1. Bioinformatics, 31(20), 3356–3358. + +- [Alakazam](https://doi.org/10.1126/scitranslmed.3008879) + + > Stern, J. N. H., Yaari, G., Vander Heiden, J. A., Church, G., Donahue, W. F., Hintzen, R. Q., … O’Connor, K. C. (2014). B cells populating the multiple sclerosis brain mature in the draining cervical lymph nodes. Science Translational Medicine, 6(248). + +- [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) + +- [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/) + + > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924. + +## Software packaging/containerisation tools + +- [Anaconda](https://anaconda.com) + + > Anaconda Software Distribution. Computer software. Vers. 2-2.4.0. Anaconda, Nov. 2016. Web. + +- [Bioconda](https://pubmed.ncbi.nlm.nih.gov/29967506/) + + > Grüning B, Dale R, Sjödin A, Chapman BA, Rowe J, Tomkins-Tinch CH, Valieris R, Köster J; Bioconda Team. Bioconda: sustainable and comprehensive software distribution for the life sciences. Nat Methods. 2018 Jul;15(7):475-476. doi: 10.1038/s41592-018-0046-7. PubMed PMID: 29967506. + +- [BioContainers](https://pubmed.ncbi.nlm.nih.gov/28379341/) + + > da Veiga Leprevost F, Grüning B, Aflitos SA, Röst HL, Uszkoreit J, Barsnes H, Vaudel M, Moreno P, Gatto L, Weber J, Bai M, Jimenez RC, Sachsenberg T, Pfeuffer J, Alvarez RV, Griss J, Nesvizhskii AI, Perez-Riverol Y. BioContainers: an open-source and community-driven framework for software standardization. Bioinformatics. 2017 Aug 15;33(16):2580-2582. doi: 10.1093/bioinformatics/btx192. PubMed PMID: 28379341; PubMed Central PMCID: PMC5870671. + +- [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241) + +- [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/) + + > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675. + diff --git a/bin/execute_report.R b/bin/execute_report.R index 211f8f30..8c80823a 100755 --- a/bin/execute_report.R +++ b/bin/execute_report.R @@ -1,9 +1,15 @@ #!/usr/bin/env Rscript library(rmarkdown) +library(optparse) -args = commandArgs(trailingOnly=TRUE) +option_list = list( + make_option(c("-r", "--report_file"), type="character", default=NULL, help="report rmarkdown file", metavar="character") +) + +opt_parser = OptionParser(option_list=option_list) +opt = parse_args(opt_parser) wd=getwd() -rmarkdown::render(args[1], output_file = "Bcellmagic_report.html", knit_root_dir = wd, output_dir = wd) +rmarkdown::render(opt$report_file, output_file = "Bcellmagic_report.html", knit_root_dir = wd, output_dir = wd) diff --git a/modules/local/alakazam/alakazam_shazam_repertoires.nf b/modules/local/alakazam/alakazam_shazam_repertoires.nf index 0f3fea1b..4d9fe91a 100644 --- a/modules/local/alakazam/alakazam_shazam_repertoires.nf +++ b/modules/local/alakazam/alakazam_shazam_repertoires.nf @@ -2,15 +2,15 @@ process ALAKAZAM_SHAZAM_REPERTOIRES { tag "report" label 'process_high' - conda (params.enable_conda ? "conda-forge::r-base=4.1.2 bioconda::r-alakazam=1.2.0 bioconda::r-shazam=1.1.0 conda-forge::r-kableextra=1.3.4 conda-forge::r-knitr=1.33 conda-forge::r-stringr=1.4.0 conda-forge::r-dplyr=1.0.6" : null) + conda (params.enable_conda ? "conda-forge::r-base=4.1.2 bioconda::r-alakazam=1.2.0 bioconda::r-shazam=1.1.0 conda-forge::r-kableextra=1.3.4 conda-forge::r-knitr=1.33 conda-forge::r-stringr=1.4.0 conda-forge::r-dplyr=1.0.6 conda-forge::r-optparse=1.7.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-3c44411d6bed445c86c3f3bb91b5464377669d0f:37d81bcb128d0d1b27c8746e089087e19ddfe3fb-0' : - 'quay.io/biocontainers/mulled-v2-3c44411d6bed445c86c3f3bb91b5464377669d0f:37d81bcb128d0d1b27c8746e089087e19ddfe3fb-0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-7da73314bcc47157b442d16c3dcfbe81e75a404f:9bb35f8114dffcd97b3afb5de8587355aca16b66-0' : + 'quay.io/biocontainers/mulled-v2-7da73314bcc47157b442d16c3dcfbe81e75a404f:9bb35f8114dffcd97b3afb5de8587355aca16b66-0' }" input: path(tab) // sequence tsv table in AIRR format path("Table_sequences.tsv") - path(repertoire_report) + tuple path(repertoire_report), path(css), path(logo) output: path "versions.yml" , emit: versions @@ -19,7 +19,7 @@ process ALAKAZAM_SHAZAM_REPERTOIRES { script: """ - execute_report.R ${repertoire_report} + execute_report.R --report_file ${repertoire_report} cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/workflows/bcellmagic.nf b/workflows/bcellmagic.nf index a69a8d64..bdc0e1f6 100644 --- a/workflows/bcellmagic.nf +++ b/workflows/bcellmagic.nf @@ -131,7 +131,6 @@ ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multi // Rmarkdown report file ch_rmarkdown_report = Channel.fromPath( ["$projectDir/assets/repertoire_comparison.Rmd", - "$projectDir/assets/references.bibtex", "$projectDir/assets/nf-core_style.css", "$projectDir/assets/nf-core-airrflow_logo_light.png"], checkIfExists: true)