{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T07:54:31Z","timestamp":1772265271497,"version":"3.50.1"},"posted":{"date-parts":[[2015,3,12]]},"group-title":"PeerJ PrePrints","reference-count":0,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2015,3,12]],"date-time":"2015-03-12T00:00:00Z","timestamp":1426118400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                  We present a semi-streaming algorithm for k-mer spectral analysis of DNA sequencing reads, together with a derivative approach that is fully streaming. The approach can also be applied to genomic, transcriptomic, and metagenomic data sets. We develop two tools for short-read analysis based on these approaches, a method for semi-streaming k-mer-based error trimming, and a method for the analysis of error profiles in short reads using a streaming sublinear approach. These tools are implemented in the khmer software package, which is freely available under the BSD License at\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/ged-lab\/khmer\/\">github.com\/ged-lab\/khmer\/<\/jats:ext-link>\n                  .\n                <\/jats:p>","DOI":"10.7287\/peerj.preprints.890v1","type":"posted-content","created":{"date-parts":[[2018,1,12]],"date-time":"2018-01-12T15:45:06Z","timestamp":1515771906000},"source":"Crossref","is-referenced-by-count":8,"title":["Crossing the streams: a framework for streaming analysis of short DNA sequencing reads"],"prefix":"10.7287","author":[{"given":"Qingpeng","family":"Zhang","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Michigan State University, East Lansing, Michigan, USA"}]},{"given":"Sherine","family":"Awad","sequence":"additional","affiliation":[{"name":"Microbiology and Molecular Genetics, Michigan State University, East Lansing, Michigan, USA"},{"name":"Population Health and Reproduction, University of California, Davis, Davis, California, USA"}]},{"given":"C. Titus","family":"Brown","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Michigan State University, East Lansing, Michigan, USA"},{"name":"Microbiology and Molecular Genetics, Michigan State University, East Lansing, Michigan, USA"},{"name":"Population Health and Reproduction, University of California, Davis, Davis, California, USA"}]}],"member":"4443","container-title":[],"original-title":[],"link":[{"URL":"https:\/\/peerj.com\/preprints\/890v1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/preprints\/890v1.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/preprints\/890v1.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/preprints\/890v1.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T13:05:00Z","timestamp":1577106300000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/preprints\/890v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3,12]]},"references-count":0,"aliases":["10.7287\/peerj.preprints.890"],"URL":"https:\/\/doi.org\/10.7287\/peerj.preprints.890v1","relation":{"is-cited-by":[{"id-type":"doi","id":"10.21105\/joss.00272","asserted-by":"object"},{"id-type":"doi","id":"10.3389\/fmicb.2017.02384","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2015,3,12]]},"subtype":"preprint"}}