{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:50:00Z","timestamp":1771048200612,"version":"3.50.1"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2018,2,13]],"date-time":"2018-02-13T00:00:00Z","timestamp":1518480000000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000268","name":"BBSRC","doi-asserted-by":"publisher","award":["BB\/L020858\/1"],"award-info":[{"award-number":["BB\/L020858\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU-METASPACE","award":["34402"],"award-info":[{"award-number":["34402"]}]},{"name":"Imperial College Stratified Medicine Graduate Training Programme in Systems Medicine and Spectroscopic Profiling"},{"name":"STRATiGRAD"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>High-resolution mass spectrometry permits simultaneous detection of thousands of different metabolites in biological samples; however, their automated annotation still presents a challenge due to the limited number of tailored computational solutions freely available to the scientific community.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here, we introduce ChemDistiller, a customizable engine that combines automated large-scale annotation of metabolites using tandem MS data with a compiled database containing tens of millions of compounds with pre-calculated \u2018fingerprints\u2019 and fragmentation patterns. Our tests using publicly and commercially available tandem MS spectra for reference compounds show retrievals rates comparable to or exceeding the ones obtainable by the current state-of-the-art solutions in the field while offering higher throughput, scalability and processing speed.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Source code freely available for download at https:\/\/bitbucket.org\/iAnalytica\/chemdistillerpython.<\/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\/bty080","type":"journal-article","created":{"date-parts":[[2018,2,12]],"date-time":"2018-02-12T12:19:12Z","timestamp":1518437952000},"page":"2096-2102","source":"Crossref","is-referenced-by-count":50,"title":["ChemDistiller: an engine for metabolite annotation in mass spectrometry"],"prefix":"10.1093","volume":"34","author":[{"given":"Ivan","family":"Laponogov","sequence":"first","affiliation":[{"name":"Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"}]},{"given":"Noureddin","family":"Sadawi","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"}]},{"given":"Dieter","family":"Galea","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"}]},{"given":"Reza","family":"Mirnezami","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"}]},{"given":"Kirill A","family":"Veselkov","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"}]}],"member":"286","published-online":{"date-parts":[[2018,2,12]]},"reference":[{"key":"2023012713395637600_bty080-B1","doi-asserted-by":"crossref","first-page":"W94","DOI":"10.1093\/nar\/gku436","article-title":"CFM-ID: a web server for annotation, spectrum prediction and metabolite identification from tandem mass spectra","volume":"42(Web Server issue)","author":"Allen","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B2","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11306-014-0676-4","article-title":"Competitive fragmentation modeling of ESI\u2013MS\/MS spectra for putative metabolite identification","volume":"11","author":"Allen","year":"2015","journal-title":"Metabolomics"},{"key":"2023012713395637600_bty080-B3","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1093\/bioinformatics\/btn603","article-title":"SIRIUS: decomposing isotope patterns for metabolite identification","volume":"25","author":"Bocker","year":"2009","journal-title":"Bioinformatics"},{"key":"2023012713395637600_bty080-B4","article-title":"LIBSVM","volume":"2","author":"Chang","year":"2011","journal-title":"A library for support vector machines. ACM TIST"},{"key":"2023012713395637600_bty080-B5","first-page":"D344","article-title":"ChEBI: a database and ontology for chemical entities of biological interest","volume":"36(Database issue)","author":"Degtyarenko","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B6","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1111\/tpj.13422","article-title":"High spatial resolution mass spectrometry imaging reveals the genetically programmed, developmental modification of the distribution of thylakoid membrane lipids among individual cells of maize leaf","volume":"89","author":"Duenas","year":"2017","journal-title":"Plant J"},{"key":"2023012713395637600_bty080-B7","doi-asserted-by":"crossref","first-page":"12580","DOI":"10.1073\/pnas.1509788112","article-title":"Searching molecular structure databases with tandem mass spectra using CSI: fingerID","volume":"112","author":"D\u00fchrkop","year":"2015","journal-title":"Proc. Natl. Acad. Sci"},{"key":"2023012713395637600_bty080-B8","doi-asserted-by":"crossref","first-page":"W606","DOI":"10.1093\/nar\/gkm324","article-title":"LIPID MAPS online tools for lipid research","volume":"35(Web Server issue)","author":"Fahy","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B9","doi-asserted-by":"crossref","first-page":"D625","DOI":"10.1093\/nar\/gks992","article-title":"ECMDB: the E. coli metabolome database","volume":"41","author":"Guo","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B10","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/1758-2946-5-7","article-title":"InChI\u2013the worldwide chemical structure identifier standard","volume":"5","author":"Heller","year":"2013","journal-title":"J. Cheminform"},{"key":"2023012713395637600_bty080-B11","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1002\/jms.1777","article-title":"MassBank: a public repository for sharing mass spectral data for life sciences","volume":"45","author":"Horai","year":"2010","journal-title":"J. Mass Spectrom"},{"key":"2023012713395637600_bty080-B12","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1021\/ci049714+","article-title":"ZINC - a free database of commercially available compounds for virtual screening","volume":"45","author":"Irwin","year":"2005","journal-title":"J. Chem. Inf. Model"},{"key":"2023012713395637600_bty080-B13","doi-asserted-by":"crossref","first-page":"44.","DOI":"10.1186\/s13321-015-0087-1","article-title":"MINEs: open access databases of computationally predicted enzyme promiscuity products for untargeted metabolomics","volume":"7","author":"Jeffryes","year":"2015","journal-title":"J. Cheminform"},{"key":"2023012713395637600_bty080-B14","doi-asserted-by":"crossref","first-page":"D815","DOI":"10.1093\/nar\/gkr916","article-title":"YMDB: the yeast metabolome database","volume":"40(Database issue)","author":"Jewison","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B15","doi-asserted-by":"crossref","first-page":"D1202","DOI":"10.1093\/nar\/gkv951","article-title":"PubChem substance and compound databases","volume":"44","author":"Kim","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B16","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open Babel: an open chemical toolbox","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"J. Cheminform"},{"key":"2023012713395637600_bty080-B17","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nmeth.4072","article-title":"FDR-controlled metabolite annotation for high-resolution imaging mass spectrometry","volume":"14","author":"Palmer","year":"2017","journal-title":"Nat. Methods"},{"key":"2023012713395637600_bty080-B18","doi-asserted-by":"crossref","first-page":"e28966.","DOI":"10.1371\/journal.pone.0028966","article-title":"Understanding and classifying metabolite space and metabolite-likeness","volume":"6","author":"Peironcely","year":"2011","journal-title":"PLoS One"},{"key":"2023012713395637600_bty080-B19","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1186\/1471-2105-11-395","article-title":"MZmine 2: modular framework for processing, visualizing, and analyzing mass spectrometry-based molecular profile data","volume":"11","author":"Pluskal","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012713395637600_bty080-B20","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s13321-016-0115-9","article-title":"MetFrag relaunched: incorporating strategies beyond in silico fragmentation","volume":"8","author":"Ruttkies","year":"2016","journal-title":"J. Cheminform"},{"key":"2023012713395637600_bty080-B21","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1021\/ac051437y","article-title":"XCMS: processing mass spectrometry data for metabolite profiling using nonlinear peak alignment, matching, and identification","volume":"78","author":"Smith","year":"2006","journal-title":"Anal. Chem"},{"key":"2023012713395637600_bty080-B22","doi-asserted-by":"crossref","first-page":"2111","DOI":"10.2174\/138161206777585274","article-title":"Recent developments of the chemistry development kit (CDK)\u2014an open-source java library for chemo- and bio-informatics","volume":"12","author":"Steinbeck","year":"2006","journal-title":"Curr. Pharm. Des"},{"key":"2023012713395637600_bty080-B23","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comp. Sci"},{"key":"2023012713395637600_bty080-B24","first-page":"D801","article-title":"HMDB 3.0\u2013the human metabolome database in 2013","volume":"41(Database issue)","author":"Wishart","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023012713395637600_bty080-B25","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1186\/1471-2105-11-148","article-title":"In silico fragmentation for computer assisted identification of metabolite mass spectra","volume":"11","author":"Wolf","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012713395637600_bty080-B26","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1104\/pp.110.157396","article-title":"Creation of a genome-wide metabolic pathway database for Populus trichocarpa using a new approach for reconstruction and curation of metabolic pathways for plants","volume":"153","author":"Zhang","year":"2010","journal-title":"Plant Physiol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/12\/2096\/48936080\/bioinformatics_34_12_2096.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/12\/2096\/48936080\/bioinformatics_34_12_2096.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T14:21:07Z","timestamp":1674829267000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/12\/2096\/4852828"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2018,2,12]]},"references-count":26,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2018,6,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty080","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,6,15]]},"published":{"date-parts":[[2018,2,12]]}}}