{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:09:36Z","timestamp":1762542576925},"reference-count":8,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2016,9,22]],"date-time":"2016-09-22T00:00:00Z","timestamp":1474502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,1,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Data-parallel programming techniques can dramatically decrease the time needed to analyze large datasets. While these methods have provided significant improvements for sequencing-based analyses, other areas of biological informatics have not yet adopted them. Here, we introduce Biospark, a new framework for performing data-parallel analysis on large numerical datasets. Biospark builds upon the open source Hadoop and Spark projects, bringing domain-specific features for biology.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>Source code is licensed under the Apache 2.0 open source license and is available at the project website: https:\/\/www.assembla.com\/spaces\/roberts-lab-public\/wiki\/Biospark<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btw614","type":"journal-article","created":{"date-parts":[[2016,9,24]],"date-time":"2016-09-24T01:11:09Z","timestamp":1474679469000},"page":"303-305","source":"Crossref","is-referenced-by-count":17,"title":["Biospark: scalable analysis of large numerical datasets from biological simulations and experiments using Hadoop and Spark"],"prefix":"10.1093","volume":"33","author":[{"given":"Max","family":"Klein","sequence":"first","affiliation":[{"name":"Department of Biophysics, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rati","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Biophysics, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris H","family":"Bohrer","sequence":"additional","affiliation":[{"name":"Department of Biophysics, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cameron M","family":"Avelis","sequence":"additional","affiliation":[{"name":"Department of Biophysics, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elijah","family":"Roberts","sequence":"additional","affiliation":[{"name":"Department of Biophysics, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,9,22]]},"reference":[{"key":"2023020204302814200_btw614-B1","author":"Dean","year":"2004"},{"key":"2023020204302814200_btw614-B2","author":"Ekanayake","year":"2008"},{"key":"2023020204302814200_btw614-B3","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":"2023020204302814200_btw614-B4","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1093\/bioinformatics\/bts054","article-title":"Hadoop-BAM: directly manipulating next generation sequencing data in the cloud","volume":"28","author":"Niemenmaa","year":"2012","journal-title":"Bioinformatics"},{"key":"2023020204302814200_btw614-B5","doi-asserted-by":"crossref","first-page":"3014","DOI":"10.1093\/bioinformatics\/btt528","article-title":"BioPig: a Hadoop-based analytic toolkit for large-scale sequence data","volume":"29","author":"Nordberg","year":"2013","journal-title":"Bioinformatics"},{"key":"2023020204302814200_btw614-B6","author":"Nothaft","year":"2015"},{"key":"2023020204302814200_btw614-B7","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1016\/j.jbi.2013.07.001","article-title":"Big data\u2019, Hadoop and cloud computing in genomics","volume":"46","author":"O\u2019Driscoll","year":"2013","journal-title":"J. Biomed. Inf"},{"key":"2023020204302814200_btw614-B8","author":"Zaharia","year":"2012"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/2\/303\/49037141\/bioinformatics_33_2_303.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/2\/303\/49037141\/bioinformatics_33_2_303.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T04:30:40Z","timestamp":1675312240000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/2\/303\/2525719"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2016,9,22]]},"references-count":8,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,1,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btw614","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,1,15]]},"published":{"date-parts":[[2016,9,22]]}}}