{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:55:21Z","timestamp":1773802521104,"version":"3.50.1"},"reference-count":23,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T00:00:00Z","timestamp":1707609600000},"content-version":"vor","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30CA016042"],"award-info":[{"award-number":["P30CA016042"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA244729"],"award-info":[{"award-number":["R01CA244729"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA270108"],"award-info":[{"award-number":["R01CA270108"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U2CCA271894"],"award-info":[{"award-number":["U2CCA271894"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U24CA248265"],"award-info":[{"award-number":["U24CA248265"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U54HG012517"],"award-info":[{"award-number":["U54HG012517"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000005","name":"Department of Defense","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UCLA Institute for Precision Health"},{"DOI":"10.13039\/100007186","name":"UCLA Jonsson Comprehensive Cancer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007186","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The ongoing expansion in the volume of biomedical data has contributed to a growing complexity in the tools and technologies used in research with an increased reliance on complex workflows written in orchestration languages such as Nextflow to integrate algorithms into processing pipelines. The growing use of workflows involving various tools and algorithms has led to increased scrutiny of software development practices to avoid errors in individual tools and in the connections between them.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To facilitate test-driven development of Nextflow pipelines, we created NFTest, a framework for automated pipeline testing and validation with customizability options for Nextflow features. It is open-source, easy to initialize and use, and customizable to allow for testing of complex workflows with test success configurable through a broad range of assertions. NFTest simplifies the testing burden on developers by automating tests once defined and providing a flexible interface for running tests to validate workflows. This reduces the barrier to rigorous biomedical workflow testing and paves the way toward reducing computational errors in biomedicine.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>NFTest is an open-source Python framework under the GPLv2 license and is freely available at https:\/\/github.com\/uclahs-cds\/tool-NFTest. The call-sSNV Nextflow pipeline is available at: https:\/\/github.com\/uclahs-cds\/pipeline-call-sSNV.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae081","type":"journal-article","created":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T10:30:23Z","timestamp":1707647423000},"source":"Crossref","is-referenced-by-count":20,"title":["NFTest: automated testing of Nextflow pipelines"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3113-7010","authenticated-orcid":false,"given":"Yash","family":"Patel","sequence":"first","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"given":"Chenghao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Department of Human Genetics, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1082-3871","authenticated-orcid":false,"given":"Takafumi N","family":"Yamaguchi","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Department of Human Genetics, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"given":"Yuan Zhe","family":"Bugh","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"given":"Mao","family":"Tian","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Department of Human Genetics, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1012-7879","authenticated-orcid":false,"given":"Aaron","family":"Holmes","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"given":"Sorel T","family":"Fitz-Gibbon","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Department of Human Genetics, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0553-7520","authenticated-orcid":false,"given":"Paul C","family":"Boutros","sequence":"additional","affiliation":[{"name":"Jonsson Comprehensive Cancer Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Institute for Precision Health, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Department of Human Genetics, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Department of Urology, University of California, Los Angeles , Los Angeles, CA 90095, United States"},{"name":"Broad Stem Cell Research Center, University of California, Los Angeles , Los Angeles, CA 90095, United States"}]}],"member":"286","published-online":{"date-parts":[[2024,2,10]]},"reference":[{"key":"2024022120061853200_btae081-B1","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.entcs.2005.12.014","article-title":"An introduction to software testing","volume":"148","author":"Baresi","year":"2006","journal-title":"Electron Notes Theor Comput Sci"},{"key":"2024022120061853200_btae081-B2","author":"Broad Institute","year":"2019"},{"key":"2024022120061853200_btae081-B3","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/1471-2105-12-35","article-title":"VennDiagram: a package for the generation of highly-customizable Venn and Euler diagrams in R","volume":"12","author":"Chen","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2024022120061853200_btae081-B4","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.crbiot.2022.02.004","article-title":"Big data: historic advances and emerging trends in biomedical research","volume":"4","author":"Cremin","year":"2022","journal-title":"Curr Res Biotechnol"},{"key":"2024022120061853200_btae081-B5","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3486897","article-title":"Methods included: standardizing computational reuse and portability with the common workflow language","volume":"65","author":"Crusoe","year":"2022","journal-title":"Commun ACM"},{"key":"2024022120061853200_btae081-B6","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","article-title":"The variant call format and VCFtools","volume":"27","author":"Danecek","year":"2011","journal-title":"Bioinformatics"},{"key":"2024022120061853200_btae081-B7","doi-asserted-by":"crossref","first-page":"giab008","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and BCFtools","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"2024022120061853200_btae081-B8","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s40537-019-0217-0","article-title":"Big data in healthcare: management, analysis and future prospects","volume":"6","author":"Dash","year":"2019","journal-title":"J Big Data"},{"key":"2024022120061853200_btae081-B9","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1038\/nbt.3820","article-title":"Nextflow enables reproducible computational workflows","volume":"35","author":"Di Tommaso","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2024022120061853200_btae081-B10","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1186\/s13059-016-1029-6","article-title":"MuSE: accounting for tumor heterogeneity using a sample-specific error model improves sensitivity and specificity in mutation calling from sequencing data","volume":"17","author":"Fan","year":"2016","journal-title":"Genome Biol"},{"key":"2024022120061853200_btae081-B11","doi-asserted-by":"crossref","first-page":"63","DOI":"10.12688\/f1000research.16665.2","article-title":"Sarek: a portable workflow for whole-genome sequencing analysis of germline and somatic variants [version 2; peer review: 2 approved]","volume":"9","author":"Garcia","year":"2020","journal-title":"F1000Res"},{"key":"2024022120061853200_btae081-B12","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/MC.2005.314","article-title":"Test-driven development concepts, taxonomy, and future direction","volume":"38","author":"Janzen","year":"2005","journal-title":"Computer"},{"key":"2024022120061853200_btae081-B13","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1038\/s41592-018-0051-x","article-title":"Strelka2: fast and accurate calling of germline and somatic variants","volume":"15","author":"Kim","year":"2018","journal-title":"Nat Methods"},{"key":"2024022120061853200_btae081-B14","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1093\/bioinformatics\/bts480","article-title":"Snakemake\u2014a scalable bioinformatics workflow engine","volume":"28","author":"K\u00f6ster","year":"2012","journal-title":"Bioinformatics"},{"key":"2024022120061853200_btae081-B15","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1093\/bioinformatics\/btr665","article-title":"SomaticSniper: identification of somatic point mutations in whole genome sequencing data","volume":"28","author":"Larson","year":"2012","journal-title":"Bioinformatics"},{"key":"2024022120061853200_btae081-B16","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2024022120061853200_btae081-B17","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/MS.2006.114","article-title":"Static code analysis","volume":"23","author":"Louridas","year":"2006","journal-title":"IEEE Softw"},{"key":"2024022120061853200_btae081-B18","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The genome analysis toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res"},{"key":"2024022120061853200_btae081-B19","author":"Patel"},{"key":"2024022120061853200_btae081-B20","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1086\/519795","article-title":"PLINK: a tool set for whole-genome association and population-based linkage analyses","volume":"81","author":"Purcell","year":"2007","journal-title":"Am J Hum Genet"},{"key":"2024022120061853200_btae081-B21","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1038\/s41587-019-0364-z","article-title":"A community effort to create standards for evaluating tumor subclonal reconstruction","volume":"38","author":"Salcedo","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2024022120061853200_btae081-B22","doi-asserted-by":"crossref","first-page":"273","DOI":"10.12688\/f1000research.10750.2","article-title":"General guidelines for biomedical software development","volume":"6","author":"Silva","year":"2017","journal-title":"F1000Res"},{"key":"2024022120061853200_btae081-B23","doi-asserted-by":"crossref","first-page":"W354","DOI":"10.1093\/nar\/gkac247","article-title":"The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update","volume":"50","author":"The Galaxy Community","year":"2022","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae081\/56659514\/btae081.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/2\/btae081\/56731951\/btae081.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/2\/btae081\/56731951\/btae081.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T20:06:39Z","timestamp":1708545999000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae081\/7606335"}},"subtitle":[],"editor":[{"given":"Peter","family":"Robinson","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae081","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,2,1]]},"published":{"date-parts":[[2024,2,1]]},"article-number":"btae081"}}