{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T22:49:05Z","timestamp":1779230945540,"version":"3.51.4"},"reference-count":9,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":1404,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Summary: READSCAN is a highly scalable parallel program to identify non-host sequences (of potential pathogen origin) and estimate their genome relative abundance in high-throughput sequence datasets. READSCAN accurately classified human and viral sequences on a 20.1 million reads simulated dataset in &amp;lt;27 min using a small Beowulf compute cluster with 16 nodes (Supplementary Material).<\/jats:p>\n               <jats:p>Availability: \u00a0http:\/\/cbrc.kaust.edu.sa\/readscan<\/jats:p>\n               <jats:p>Contact: \u00a0arnab.pain@kaust.edu.sa or raeece.naeem@gmail.com<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/bts684","type":"journal-article","created":{"date-parts":[[2012,11,29]],"date-time":"2012-11-29T02:51:55Z","timestamp":1354157515000},"page":"391-392","source":"Crossref","is-referenced-by-count":46,"title":["READSCAN: a fast and scalable pathogen discovery program with accurate genome relative abundance estimation"],"prefix":"10.1093","volume":"29","author":[{"given":"Raeece","family":"Naeem","sequence":"first","affiliation":[{"name":"Pathogen Genomics Laboratory, Computational Bioscience Research Center, King Abdullah University of Science and Technology (KAUST), Thuwal-23955-6900, Kingdom of Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mamoon","family":"Rashid","sequence":"additional","affiliation":[{"name":"Pathogen Genomics Laboratory, Computational Bioscience Research Center, King Abdullah University of Science and Technology (KAUST), Thuwal-23955-6900, Kingdom of Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnab","family":"Pain","sequence":"additional","affiliation":[{"name":"Pathogen Genomics Laboratory, Computational Bioscience Research Center, King Abdullah University of Science and Technology (KAUST), Thuwal-23955-6900, Kingdom of Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2012,11,28]]},"reference":[{"key":"2023012810213388400_bts684-B1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/0020-0190(96)00083-X","article-title":"Fast and practical approximate string matching","volume":"59","author":"Baeza-Yates","year":"1996","journal-title":"Inf. Process. Lett."},{"key":"2023012810213388400_bts684-B2","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1093\/bioinformatics\/bts100","article-title":"Rapid identification of non-human sequences in high-throughput sequencing datasets","volume":"28","author":"Bhaduri","year":"2012","journal-title":"Bioinformatics"},{"key":"2023012810213388400_bts684-B3","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1186\/1471-2105-13-206","article-title":"CaPSID: a bioinformatics platform for computational pathogen sequence identification in human genomes and transcriptomes","volume":"13","author":"Borozan","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2023012810213388400_bts684-B4","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1101\/gr.126516.111","article-title":"Fusobacterium nucleatum infection is prevalent in human colorectal carcinoma","volume":"22","author":"Castellarin","year":"2012","journal-title":"Genome Res."},{"key":"2023012810213388400_bts684-B5","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1038\/nbt.1868","article-title":"PathSeq: software to identify or discover microbes by deep sequencing of human tissue","volume":"29","author":"Kostic","year":"2011","journal-title":"Nat. Biotechnol."},{"key":"2023012810213388400_bts684-B6","doi-asserted-by":"crossref","first-page":"e36427","DOI":"10.1371\/journal.pone.0036427","article-title":"Optimizing read mapping to reference genomes to determine composition and species prevalence in microbial communities","volume":"7","author":"Martin","year":"2012","journal-title":"PLoS One"},{"key":"2023012810213388400_bts684-B7","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1038\/nbt.1914","article-title":"Transcriptome sequencing across a prostate cancer cohort identifies PCAT-1, an unannotated lincRNA implicated in disease progression","volume":"29","author":"Prensner","year":"2011","journal-title":"Nat. Biotechnol."},{"key":"2023012810213388400_bts684-B8","doi-asserted-by":"crossref","first-page":"e27992","DOI":"10.1371\/journal.pone.0027992","article-title":"Accurate genome relative abundance estimation based on shotgun metagenomic reads","volume":"6","author":"Xia","year":"2011","journal-title":"PLoS One"},{"key":"2023012810213388400_bts684-B9","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s10586-010-0134-7","article-title":"Harnessing parallelism in multicore clusters with the All-Pairs, Wavefront, and Makeflow abstractions","volume":"13","author":"Yu","year":"2010","journal-title":"Cluster Comput."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/3\/391\/48892648\/bioinformatics_29_3_391.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/29\/3\/391\/48892648\/bioinformatics_29_3_391.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T11:41:46Z","timestamp":1674906106000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/29\/3\/391\/257042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,28]]},"references-count":9,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,2,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bts684","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2013,2,1]]},"published":{"date-parts":[[2012,11,28]]}}}