{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T02:21:18Z","timestamp":1771294878878,"version":"3.50.1"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T00:00:00Z","timestamp":1688688000000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"crossref","award":["1759831"],"award-info":[{"award-number":["1759831"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Tau-typing is an integrated analysis pipeline for identifying genes or genomic segments whose phylogenetic resolving power most closely resembles the genome-wide resolving power of an input collection of genomes using the Kendall Tau rank correlation statistic. The pipeline is implemented in Nextflow and uses Docker and Singularity containers to ensure reliable scalability and reproducibility of results. This pipeline is particularly suitable for organisms for which whole-genome sequencing remains unaffordable or unscalable for routine applications, such as protozoan parasites which are not amenable to laboratory culture-based methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Tau-typing is freely available at https:\/\/github.com\/hseabolt\/tautyping. The pipeline is implemented in Nextflow with Singularity support.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad425","type":"journal-article","created":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T13:04:13Z","timestamp":1688735053000},"source":"Crossref","is-referenced-by-count":2,"title":["Tau-typing: a Nextflow pipeline for finding the best phylogenetic markers in the genome for molecular typing of microbial species"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0336-5545","authenticated-orcid":false,"given":"Matthew H","family":"Seabolt","sequence":"first","affiliation":[{"name":"Leidos Inc. , Reston, VA 20190, United States"},{"name":"School of Biological Sciences, Georgia Institute of Technology , Atlanta, GA 30332, United States"}]},{"given":"Arun K","family":"Boddapati","sequence":"additional","affiliation":[{"name":"Leidos Inc. , Reston, VA 20190, United States"}]},{"given":"Joshua J","family":"Forstedt","sequence":"additional","affiliation":[{"name":"Leidos Inc. , Reston, VA 20190, United States"}]},{"given":"Konstantinos T","family":"Konstantinidis","sequence":"additional","affiliation":[{"name":"School of Biological Sciences, Georgia Institute of Technology , Atlanta, GA 30332, United States"},{"name":"School of Civil and Environmental Engineering, Georgia Institute of Technology , Atlanta, GA 30332, United States"}]}],"member":"286","published-online":{"date-parts":[[2023,7,7]]},"reference":[{"key":"2023071202310772300_btad425-B1","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.1056\/NEJMsr1813907","article-title":"Pathogen genomics in public health","volume":"381","author":"Armstrong","year":"2019","journal-title":"N Engl J Med"},{"key":"2023071202310772300_btad425-B2","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1021\/acs.jproteome.0c00904","article-title":"BioContainers Registry: searching bioinformatics and proteomics tools, packages, and containers","volume":"20","author":"Bai","year":"2021","journal-title":"J Proteome Res"},{"key":"2023071202310772300_btad425-B3","doi-asserted-by":"crossref","first-page":"giz119","DOI":"10.1093\/gigascience\/giz119","article-title":"PIRATE: a fast and scalable pangenomics toolbox for clustering diverged orthologues in bacteria","volume":"8","author":"Bayliss","year":"2019","journal-title":"Gigascience"},{"key":"2023071202310772300_btad425-B4","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1186\/1471-2105-10-421","article-title":"BLAST+: architecture and applications","volume":"10","author":"Camacho","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2023071202310772300_btad425-B5","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":"2023071202310772300_btad425-B6","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1016\/j.tim.2022.02.001","article-title":"Genome-powered classification of microbial eukaryotes: focus on coral algal symbionts","volume":"30","author":"Dougan","year":"2022","journal-title":"Trends Microbiol"},{"key":"2023071202310772300_btad425-B7","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1002\/gch2.1018","article-title":"Data, disease and diplomacy: GISAID\u2019s innovative contribution to global health","volume":"1","author":"Elbe","year":"2017","journal-title":"Glob Chall"},{"key":"2023071202310772300_btad425-B8","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1038\/s41587-020-0439-x","article-title":"The NF-core framework for community-curated bioinformatics pipelines","volume":"38","author":"Ewels","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2023071202310772300_btad425-B9","doi-asserted-by":"crossref","first-page":"3047","DOI":"10.1093\/bioinformatics\/btw354","article-title":"MultiQC: summarize analysis results for multiple tools and samples in a single report","volume":"32","author":"Ewels","year":"2016","journal-title":"Bioinformatics"},{"key":"2023071202310772300_btad425-B10","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1038\/s41592-018-0046-7","article-title":"Bioconda: sustainable and comprehensive software distribution for the life sciences","volume":"15","author":"Gr\u00fcning","year":"2018","journal-title":"Nat Methods"},{"key":"2023071202310772300_btad425-B11","doi-asserted-by":"crossref","first-page":"5114","DOI":"10.1038\/s41467-018-07641-9","article-title":"High throughput ANI analysis of 90K prokaryotic genomes reveals clear species boundaries","volume":"9","author":"Jain","year":"2018","journal-title":"Nat Commun"},{"key":"2023071202310772300_btad425-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-11-595","article-title":"BIGSdb: scalable analysis of bacterial genome variation at the population level","volume":"11","author":"Jolley","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023071202310772300_btad425-B13","doi-asserted-by":"crossref","first-page":"R808","DOI":"10.1016\/j.cub.2019.07.031","article-title":"Progress towards the tree of eukaryotes","volume":"29","author":"Keeling","year":"2019","journal-title":"Curr Biol"},{"key":"2023071202310772300_btad425-B14","doi-asserted-by":"crossref","first-page":"7286","DOI":"10.1128\/AEM.01398-06","article-title":"Toward a more robust assessment of intraspecies diversity, using fewer genetic markers","volume":"72","author":"Konstantinidis","year":"2006","journal-title":"Appl Environ Microbiol"},{"key":"2023071202310772300_btad425-B15","doi-asserted-by":"crossref","first-page":"e0177459","DOI":"10.1371\/journal.pone.0177459","article-title":"Singularity: scientific containers for mobility of compute","volume":"12","author":"Kurtzer","year":"2017","journal-title":"PLoS One"},{"key":"2023071202310772300_btad425-B16","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1038\/s41579-020-0394-z","article-title":"Bat-borne virus diversity, spillover and emergence","volume":"18","author":"Letko","year":"2020","journal-title":"Nat Rev Microbiol"},{"key":"2023071202310772300_btad425-B17","doi-asserted-by":"crossref","first-page":"360","DOI":"10.3389\/fpubh.2019.00360","article-title":"Direct sequencing of Cryptosporidium in stool samples for public health","volume":"7","author":"Morris","year":"2019","journal-title":"Front Public Health"},{"key":"2023071202310772300_btad425-B18","doi-asserted-by":"crossref","first-page":"304","DOI":"10.12688\/f1000research.23297.1","article-title":"GFF utilities: GffRead and GffCompare","volume":"9","author":"Pertea","year":"2020","journal-title":"F1000Res"},{"key":"2023071202310772300_btad425-B19","doi-asserted-by":"crossref","first-page":"e9490","DOI":"10.1371\/journal.pone.0009490","article-title":"FastTree 2\u2013approximately maximum-likelihood trees for large alignments","volume":"5","author":"Price","year":"2010","journal-title":"PLoS One"},{"key":"2023071202310772300_btad425-B20","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1093\/bioinformatics\/btq706","article-title":"Phangorn: phylogenetic analysis in R","volume":"27","author":"Schliep","year":"2011","journal-title":"Bioinformatics"},{"key":"2023071202310772300_btad425-B21","doi-asserted-by":"crossref","first-page":"e02275","DOI":"10.1128\/AEM.02275-20","article-title":"Hidden diversity within common protozoan parasites as revealed by a novel genomotyping scheme","volume":"87","author":"Seabolt","year":"2021","journal-title":"Appl Environ Microbiol"},{"key":"2023071202310772300_btad425-B22","author":"Seemann"},{"key":"2023071202310772300_btad425-B23","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1093\/bioinformatics\/btaa1016","article-title":"Liftoff: accurate mapping of gene annotations","volume":"37","author":"Shumate","year":"2021","journal-title":"Bioinformatics"},{"key":"2023071202310772300_btad425-B24","doi-asserted-by":"crossref","first-page":"e1003908","DOI":"10.1371\/journal.ppat.1003908","article-title":"Cryptosporidium, Giardia, Cryptococcus, Pneumocystis genetic variability: cryptic biological species or clonal near-clades?","volume":"10","author":"Tibayrenc","year":"2014","journal-title":"PLoS Pathog"},{"key":"2023071202310772300_btad425-B25","doi-asserted-by":"crossref","first-page":"e00090-18","DOI":"10.1128\/mSphere.00090-18","article-title":"Beaver fever: whole-genome characterization of waterborne outbreak and sporadic isolates to study the zoonotic transmission of giardiasis","volume":"3","author":"Tsui","year":"2018","journal-title":"Msphere"},{"key":"2023071202310772300_btad425-B26","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1038\/s41586-022-05189-9","article-title":"Pandemic-scale phylogenomics reveals the SARS-CoV-2 recombination landscape","volume":"609","author":"Turakhia","year":"2022","journal-title":"Nature"},{"key":"2023071202310772300_btad425-B27","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1128\/CMR.17.4.697-728.2004","article-title":"Mycoplasma pneumoniae and its role as a human pathogen","volume":"17","author":"Waites","year":"2004","journal-title":"Clin Microbiol Rev"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad425\/50838244\/btad425.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/7\/btad425\/50856769\/btad425.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/7\/btad425\/50856769\/btad425.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T02:31:35Z","timestamp":1689129095000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad425\/7221034"}},"subtitle":[],"editor":[{"given":"Russell","family":"Schwartz","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":27,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad425","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,7,1]]},"published":{"date-parts":[[2023,7,1]]},"article-number":"btad425"}}