{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T23:45:44Z","timestamp":1774482344158,"version":"3.50.1"},"reference-count":11,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2018,1,31]],"date-time":"2018-01-31T00:00:00Z","timestamp":1517356800000},"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":[[2018,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>In the new release of pymzML (v2.0), we have optimized the speed of this established tool for mass spectrometry data analysis to adapt to increasing amounts of data in mass spectrometry. Thus, we integrated faster libraries for numerical calculations, improved data retrieving algorithms and have optimized the source code. Importantly, to adapt to rapidly growing file sizes, we developed a generalizable compression scheme for very fast random access and applied this concept to mzML files to retrieve spectral data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>pymzML performs at par with established C programs when it comes to processing times. However, it offers the versatility of a scripting language, while adding unprecedented fast random access to compressed files. Additionally, we designed our compression scheme in such a general way that it can be applied to any field where fast random access to large data blocks in compressed files is desired.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>pymzML is freely available on https:\/\/github.com\/pymzML\/pymzML under GPL license. pymzML requires Python3.4+\u2009and optionally numpy. Documentation available on http:\/\/pymzml.readthedocs.io.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty046","type":"journal-article","created":{"date-parts":[[2018,1,30]],"date-time":"2018-01-30T12:12:50Z","timestamp":1517314370000},"page":"2513-2514","source":"Crossref","is-referenced-by-count":81,"title":["pymzML v2.0: introducing a highly compressed and seekable gzip format"],"prefix":"10.1093","volume":"34","author":[{"given":"M","family":"K\u00f6sters","sequence":"first","affiliation":[{"name":"Institute of Plant Biology and Biotechnology, WWU M\u00fcnster, M\u00fcnster, Germany"}]},{"given":"J","family":"Leufken","sequence":"additional","affiliation":[{"name":"Institute of Plant Biology and Biotechnology, WWU M\u00fcnster, M\u00fcnster, Germany"},{"name":"Max Planck Institute for Molecular Biomedicine, M\u00fcnster, Germany"}]},{"given":"S","family":"Schulze","sequence":"additional","affiliation":[{"name":"Institute of Plant Biology and Biotechnology, WWU M\u00fcnster, M\u00fcnster, Germany"}]},{"given":"K","family":"Sugimoto","sequence":"additional","affiliation":[{"name":"Institute of Plant Biology and Biotechnology, WWU M\u00fcnster, M\u00fcnster, Germany"}]},{"given":"J","family":"Klein","sequence":"additional","affiliation":[{"name":"Bioinformatics Program, Boston University, One Silber Way, Boston, MA, USA"}]},{"given":"R P","family":"Zahedi","sequence":"additional","affiliation":[{"name":"Gerald Bronfman Department of Oncology, Jewish General Hospital, McGill University, 5100 de Maisonneuve Boulevard West, Suite 720, Montreal, Quebec, Canada"},{"name":"Segal Cancer Proteomics Centre, Lady Davis Institute, Jewish General Hospital, McGill University, 3755 C\u00f4te-Sainte-Catherine Road, Montreal, Quebec, Canada"}]},{"given":"M","family":"Hippler","sequence":"additional","affiliation":[{"name":"Institute of Plant Biology and Biotechnology, WWU M\u00fcnster, M\u00fcnster, Germany"}]},{"given":"S A","family":"Leidel","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Molecular Biomedicine, M\u00fcnster, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7048-6822","authenticated-orcid":false,"given":"C","family":"Fufezan","sequence":"additional","affiliation":[{"name":"Institute of Plant Biology and Biotechnology, WWU M\u00fcnster, M\u00fcnster, Germany"},{"name":"Cellzome A GSK Company, Heidelberg, Germany"}]}],"member":"286","published-online":{"date-parts":[[2018,1,31]]},"reference":[{"key":"2023012713013453600_bty046-B1","first-page":"1052","article-title":"PymzML-Python module for high-throughput bioinformatics on mass spectrometry data","volume":"28","author":"Bald","year":"2012","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023012713013453600_bty046-B2","doi-asserted-by":"crossref","first-page":"2776","DOI":"10.1002\/pmic.200890049","article-title":"mzML: a single, unifying data format for mass spectrometer output","volume":"8","author":"Deutsch","year":"2008","journal-title":"Proteomics"},{"key":"2023012713013453600_bty046-B3","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s13361-012-0516-6","article-title":"Pyteomics \u2013 a python framework for exploratory data analysis and rapid software prototyping in proteomics","volume":"24","author":"Goloborodko","year":"2013","journal-title":"J. Am. Soc. Mass Spectrom"},{"key":"2023012713013453600_bty046-B4","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1109\/TIT.1966.1053907","article-title":"Run-length encodings","volume":"12","author":"Golomb","year":"1966","journal-title":"IEEE Transact. Inf. Theory"},{"key":"2023012713013453600_bty046-B5","doi-asserted-by":"crossref","first-page":"2534","DOI":"10.1093\/bioinformatics\/btn323","article-title":"ProteoWizard: open source software for rapid proteomics tools development","volume":"24","author":"Kessner","year":"2008","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023012713013453600_bty046-B6","doi-asserted-by":"crossref","first-page":"1604.","DOI":"10.1104\/pp.114.240648","article-title":"Proton gradient regulation5-like1-mediated cyclic electron flow is crucial for acclimation to anoxia and complementary to nonphotochemical quenching in stress adaptation","volume":"165","author":"Kukuczka","year":"2014","journal-title":"Plant Physiol"},{"key":"2023012713013453600_bty046-B7","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1109\/TCOM.1971.1090789","article-title":"Adaptive variable-length coding for efficient compression of spacecraft television data","volume":"19","author":"Rice","year":"1971","journal-title":"IEEE Trans. Commun. Technol"},{"key":"2023012713013453600_bty046-B8","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1002\/pmic.201300246","article-title":"pyOpenMS: a Python-based interface to the OpenMS mass-spectrometry algorithm library","volume":"14","author":"R\u00f6st","year":"2014","journal-title":"Proteomics"},{"key":"2023012713013453600_bty046-B9","doi-asserted-by":"crossref","first-page":"2415","DOI":"10.1093\/bioinformatics\/btv152","article-title":"Efficient visualization of high-throughput targeted proteomics experiments: tAPIR: fig. 1","volume":"31","author":"R\u00f6st","year":"2015","journal-title":"Bioinformatics"},{"key":"2023012713013453600_bty046-B10","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1038\/nmeth.3959","article-title":"OpenMS: a flexible open-source software platform for mass spectrometry data analysis","volume":"13","author":"R\u00f6st","year":"2016","journal-title":"Nat. Methods"},{"key":"2023012713013453600_bty046-B11","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1074\/mcp.O114.037879","article-title":"Numerical compression schemes for proteomics mass spectrometry data","volume":"13","author":"Teleman","year":"2014","journal-title":"Mol. Cell. Proteomics MCP"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/14\/2513\/48917812\/bioinformatics_34_14_2513.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/14\/2513\/48917812\/bioinformatics_34_14_2513.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:52:37Z","timestamp":1674827557000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/14\/2513\/4831092"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,1,31]]},"references-count":11,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2018,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty046","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,7,15]]},"published":{"date-parts":[[2018,1,31]]}}}