From fc872f15da426926414fb7629bf6660d9880ed1e Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Fri, 10 Apr 2020 17:16:35 -0500 Subject: Draft --- paper/paper.bib | 16 ++++++ paper/paper.md | 160 +++++++++++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 151 insertions(+), 25 deletions(-) diff --git a/paper/paper.bib b/paper/paper.bib index e69de29..bcb9c0b 100644 --- a/paper/paper.bib +++ b/paper/paper.bib @@ -0,0 +1,16 @@ +@book{CWL, +title = "Common Workflow Language, v1.0", +abstract = "The Common Workflow Language (CWL) is an informal, multi-vendor working group consisting of various organizations and individuals that have an interest in portability of data analysis workflows. Our goal is to create specifications that enable data scientists to describe analysis tools and workflows that are powerful, easy to use, portable, and support reproducibility.CWL builds on technologies such as JSON-LD and Avro for data modeling and Docker for portable runtime environments. CWL is designed to express workflows for data-intensive science, such as Bioinformatics, Medical Imaging, Chemistry, Physics, and Astronomy.This is v1.0 of the CWL tool and workflow specification, released on 2016-07-08", +keywords = "cwl, workflow, specification", +author = "Brad Chapman and John Chilton and Michael Heuer and Andrey Kartashov and Dan Leehr and Herv{\'e} M{\'e}nager and Maya Nedeljkovich and Matt Scales and Stian Soiland-Reyes and Luka Stojanovic", +editor = "Peter Amstutz and Crusoe, {Michael R.} and Nebojša Tijanić", +note = "Specification, product of the Common Workflow Language working group. http://www.commonwl.org/v1.0/", +year = "2016", +month = "7", +day = "8", +doi = "10.6084/m9.figshare.3115156.v2", +language = "English", +publisher = "figshare", +address = "United States", + +} \ No newline at end of file diff --git a/paper/paper.md b/paper/paper.md index caa9903..813c91b 100644 --- a/paper/paper.md +++ b/paper/paper.md @@ -1,8 +1,9 @@ --- -title: 'Public Sequence Resource for COVID-19' +title: 'CPSR: COVID-19 Public Sequence Resource' +title_short: 'CPSR: COVID-19 Public Sequence Resource' tags: - Sequencing - - COVID + - COVID-19 authors: - name: Pjotr Prins orcid: 0000-0002-8021-9162 @@ -25,16 +26,30 @@ authors: - name: Rutger Vos orcid: 0000 affiliation: 7 - - Michael Heuer + - name: Michael Heuer orcid: 0000 affiliation: 8 - + - name: Adam Novak + orcid: 0000 + affiliation: 9 + - name: Alex Kanitz + orcid: 0000 + affiliation: 10 + - name: Jerven Bolleman + orcid: 0000 + affiliation: 11 + - name: Joep de Ligt + orcid: 0000 + affiliation: 12 affiliations: - name: Department of Genetics, Genomics and Informatics, The University of Tennessee Health Science Center, Memphis, TN, USA. index: 1 - name: Curii, Boston, USA index: 2 date: 11 April 2020 +event: COVID2020 +group: Public Sequence Uploader +authors_short: Pjotr Prins & Peter Amstutz \emph{et al.} bibliography: paper.bib --- @@ -49,13 +64,48 @@ pasting above link (or yours) with https://github.com/biohackrxiv/bhxiv-gen-pdf +Note that author order will change! + --> # Introduction -As part of the one week COVID-19 Biohackathion 2020, we formed a -working group on creating a public sequence resource for Corona virus. - +As part of the COVID-19 Biohackathion 2020 we formed a working +group to create a COVID-19 Public Sequence Resource (CPSR) for +Corona virus sequences. The general idea was to create a +repository that has a low barrier to entry for uploading sequence +data using best practices. I.e., data published with a creative +commons 4.0 (CC-4.0) license with metadata using state-of-the art +standards and, perhaps most importantly, providing standardized +workflows that get triggered on upload, so that results are +immediately available in standardized data formats. + +Existing data repositories for viral data include GISAID, EBI ENA +and NCBI. These repositories allow for free sharing of data, but +do not add value in terms of running immediate +computations. Also, GISAID, at this point, has the most complete +collection of genetic sequence data of influenza viruses and +related clinical and epidemiological data through its +database. But, due to a restricted license, data submitted to +GISAID can not be used for online web services and on-the-fly +computation. In addition GISAID registration which can take weeks +and, painfully, forces users to download sequences one at a time +to do any type of analysis. In our opinion this does not fit a +pandemic scenario where fast turnaround times are key and data +analysis has to be agile. + +We managed to create a useful sequence uploader utility within +one week by leveraging existing technologies, such as the Arvados +Cloud platform [@Arvados], the Common Workflow Langauge (CWL) +[@CWL], Docker images built with Debian packages, and the many +free and open source software packages that are available for +bioinformatics. + +The source code for the CLI uploader and web uploader can be +found [here](https://github.com/arvados/bh20-seq-resource) +(FIXME: we'll have a full page). The CWL workflow definitions can +be found [here](https://github.com/hpobio-lab/viral-analysis) and +on CWL hub (FIXME). + +We aim to add more workflows to CPSR, for example to prepare +sequence data for submitting in other public repositories, such +as EBI ENA and GISAID. This will allow researchers to share data +in multiple systems without pain, circumventing current sharing +restrictions. + +# Acknowledgements + +We thank the COVID-19 BioHackathon 2020 and ELIXIR for creating a +unique event that triggered many collaborations. We thank Curii +Corporation for their financial support for creating and running +Arvados instances. We thank Amazon AWS for their financial +support to run COVID-19 workflows. We also want to thank the +other working groups in the BioHackathon who generously +contributed onthologies, workflows and software. + # References -- cgit v1.2.3