{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:04:49Z","timestamp":1760709889077,"version":"3.37.3"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T00:00:00Z","timestamp":1562544000000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["19-16-00049"],"award-info":[{"award-number":["19-16-00049"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Peptidic natural products (PNPs) are considered a promising compound class that has many applications in medicine. Recently developed mass spectrometry-based pipelines are transforming PNP discovery into a high-throughput technology. However, the current computational methods for PNP identification via database search of mass spectra are still in their infancy and could be substantially improved.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Here we present NPS, a statistical learning-based approach for scoring PNP\u2013spectrum matches. We incorporated NPS into two leading PNP discovery tools and benchmarked them on millions of natural product mass spectra. The results demonstrate more than 45% increase in the number of identified spectra and 20% more found PNPs at a false discovery rate of 1%.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>NPS is available as a command line tool and as a web application at http:\/\/cab.spbu.ru\/software\/NPS.<\/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\/btz374","type":"journal-article","created":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T02:57:31Z","timestamp":1556333851000},"page":"i315-i323","source":"Crossref","is-referenced-by-count":6,"title":["NPS: scoring and evaluating the statistical significance of peptidic natural product\u2013spectrum matches"],"prefix":"10.1093","volume":"35","author":[{"given":"Azat M","family":"Tagirdzhanov","sequence":"first","affiliation":[{"name":"Center for Algorithmic Biotechnology, St. Petersburg State University, St. Petersburg, Russia"},{"name":"Department of Higher Mathematics, St. Petersburg Electrotechnical University \u201cLETI\u201d, St. Petersburg, Russia"}]},{"given":"Alexander","family":"Shlemov","sequence":"additional","affiliation":[{"name":"Center for Algorithmic Biotechnology, St. Petersburg State University, St. Petersburg, Russia"}]},{"given":"Alexey","family":"Gurevich","sequence":"additional","affiliation":[{"name":"Center for Algorithmic Biotechnology, St. Petersburg State University, St. Petersburg, Russia"}]}],"member":"286","published-online":{"date-parts":[[2019,7,5]]},"reference":[{"key":"2023062712343805600_btz374-B1","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1039\/C2NP20085F","article-title":"Ribosomally synthesized and post-translationally modified peptide natural products: overview and recommendations for a universal nomenclature","volume":"30","author":"Arnison","year":"2013","journal-title":"Nat. Prod. Rep"},{"year":"2007","author":"Blunt","key":"2023062712343805600_btz374-B2"},{"key":"2023062712343805600_btz374-B3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s13321-016-0116-8","article-title":"Fragmentation trees reloaded","volume":"8","author":"B\u00f6cker","year":"2016","journal-title":"J. Cheminformatics"},{"key":"2023062712343805600_btz374-B4","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1093\/bioinformatics\/btn603","article-title":"SIRIUS: decomposing isotope patterns for metabolite identification","volume":"25","author":"B\u00f6cker","year":"2009","journal-title":"Bioinformatics"},{"key":"2023062712343805600_btz374-B5","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1021\/pr050147v","article-title":"Comparison of probability and likelihood models for peptide identification from tandem mass spectrometry data","volume":"4","author":"Cannon","year":"2005","journal-title":"J. Proteome Res"},{"key":"2023062712343805600_btz374-B6","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1093\/bioinformatics\/bth092","article-title":"TANDEM: matching proteins with tandem mass spectra","volume":"20","author":"Craig","year":"2004","journal-title":"Bioinformatics"},{"key":"2023062712343805600_btz374-B7","doi-asserted-by":"crossref","first-page":"12549","DOI":"10.1073\/pnas.1516878112","article-title":"Illuminating the dark matter in metabolomics","volume":"112","author":"da Silva","year":"2015","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023062712343805600_btz374-B8","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1089\/106652799318300","article-title":"De novo peptide sequencing via tandem mass spectrometry","volume":"6","author":"Dan\u010dik","year":"1999","journal-title":"J. Comput. Biol"},{"key":"2023062712343805600_btz374-B9","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. USA"},{"key":"2023062712343805600_btz374-B10","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/j.chembiol.2015.03.010","article-title":"Molecular networking and pattern-based genome mining improves discovery of biosynthetic gene clusters and their products from Salinispora species","volume":"22","author":"Duncan","year":"2015","journal-title":"Chem. Biol"},{"key":"2023062712343805600_btz374-B11","doi-asserted-by":"crossref","first-page":"207.","DOI":"10.1038\/nmeth1019","article-title":"Target-decoy search strategy for increased confidence in large-scale protein identifications by mass spectrometry","volume":"4","author":"Elias","year":"2007","journal-title":"Nat. Methods"},{"key":"2023062712343805600_btz374-B12","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/1044-0305(94)80016-2","article-title":"An approach to correlate tandem mass spectral data of peptides with amino acid sequences in a protein database","volume":"5","author":"Eng","year":"1994","journal-title":"J. Am. Soc. Mass Spectrom"},{"key":"2023062712343805600_btz374-B13","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1021\/ac048788h","article-title":"PepNovo: de novo peptide sequencing via probabilistic network modeling","volume":"77","author":"Frank","year":"2005","journal-title":"Anal. Chem"},{"key":"2023062712343805600_btz374-B14","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.chembiol.2011.12.014","article-title":"Lessons from the past and charting the future of marine natural products drug discovery and chemical biology","volume":"19","author":"Gerwick","year":"2012","journal-title":"Chem. Biol"},{"key":"2023062712343805600_btz374-B15","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s13361-012-0516-6","article-title":"Pyteomics\u2014a 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":"2023062712343805600_btz374-B16","doi-asserted-by":"crossref","DOI":"10.2174\/138620711795767857","article-title":"Small molecule databases and chemical descriptors useful in chemoinformatics: an overview","volume":"14","author":"Gozalbes","year":"2011","journal-title":"Comb. Chem. High Throughput Screen"},{"key":"2023062712343805600_btz374-B17","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1007\/s13361-011-0139-3","article-title":"Target-decoy approach and false discovery rate: when things may go wrong","volume":"22","author":"Gupta","year":"2011","journal-title":"J. Am. Soc. Mass Spectrom"},{"key":"2023062712343805600_btz374-B18","doi-asserted-by":"crossref","first-page":"319.","DOI":"10.1038\/s41564-017-0094-2","article-title":"Increased diversity of peptidic natural products revealed by modification-tolerant database search of mass spectra","volume":"3","author":"Gurevich","year":"2018","journal-title":"Nat. Microbiol"},{"key":"2023062712343805600_btz374-B19","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1021\/ac0258913","article-title":"Intensity-based statistical scorer for tandem mass spectrometry","volume":"75","author":"Havilio","year":"2003","journal-title":"Anal. Chem"},{"key":"2023062712343805600_btz374-B20","doi-asserted-by":"crossref","first-page":"PPL33.","DOI":"10.1055\/s-0034-1382669","article-title":"Informatic search for natural products (iSNAP)\u2014a dereplication and discovery tool","volume":"80","author":"Ibrahim","year":"2014","journal-title":"Planta Med"},{"key":"2023062712343805600_btz374-B21","doi-asserted-by":"crossref","first-page":"221","DOI":"10.2174\/157489312800604354","article-title":"Database searching in mass spectrometry based proteomics","volume":"7","author":"Kert\u00e9sz-Farkas","year":"2012","journal-title":"Curr. Bioinformatics"},{"key":"2023062712343805600_btz374-B22","doi-asserted-by":"crossref","first-page":"575.","DOI":"10.1038\/nature13302","article-title":"A draft map of the human proteome","volume":"509","author":"Kim","year":"2014","journal-title":"Nature"},{"key":"2023062712343805600_btz374-B23","doi-asserted-by":"crossref","first-page":"5277","DOI":"10.1038\/ncomms6277","article-title":"MS-GF+ makes progress towards a universal database search tool for proteomics","volume":"5","author":"Kim","year":"2014","journal-title":"Nat. Commun"},{"key":"2023062712343805600_btz374-B24","doi-asserted-by":"crossref","first-page":"3354","DOI":"10.1021\/pr8001244","article-title":"Spectral probabilities and generating functions of tandem mass spectra: a strike against decoy databases","volume":"7","author":"Kim","year":"2008","journal-title":"J. Proteome Res"},{"key":"2023062712343805600_btz374-B25","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1074\/mcp.M800103-MCP200","article-title":"Spectral dictionaries: integrating de novo peptide sequencing with database search of tandem mass spectra","volume":"8","author":"Kim","year":"2009","journal-title":"Mol. Cell. Proteom"},{"key":"2023062712343805600_btz374-B26","doi-asserted-by":"crossref","first-page":"53.","DOI":"10.1038\/nmeth.4512","article-title":"Identifying metabolites by integrating metabolome databases with mass spectrometry cheminformatics","volume":"15","author":"Lai","year":"2018","journal-title":"Nat. Methods"},{"key":"2023062712343805600_btz374-B27","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1038\/nature14098","article-title":"A new antibiotic kills pathogens without detectable resistance","volume":"517","author":"Ling","year":"2015","journal-title":"Nature"},{"key":"2023062712343805600_btz374-B28","doi-asserted-by":"crossref","first-page":"D1130","DOI":"10.1093\/nar\/gks1253","article-title":"StreptomeDB: a resource for natural compounds isolated from Streptomyces species","volume":"41","author":"Lucas","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023062712343805600_btz374-B29","doi-asserted-by":"crossref","first-page":"2651","DOI":"10.1021\/cr960029e","article-title":"Modular peptide synthetases involved in nonribosomal peptide synthesis","volume":"97","author":"Marahiel","year":"1997","journal-title":"Chem. Rev"},{"key":"2023062712343805600_btz374-B30","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1038\/nchembio.1890","article-title":"Minimum information about a biosynthetic gene cluster","volume":"11","author":"Medema","year":"2015","journal-title":"Nat. Chem. Biol"},{"key":"2023062712343805600_btz374-B31","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1021\/pr300453t","article-title":"A new approach to evaluating statistical significance of spectral identifications","volume":"12","author":"Mohimani","year":"2013","journal-title":"J. Proteome Res"},{"key":"2023062712343805600_btz374-B32","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1021\/cb500199h","article-title":"Automated genome mining of ribosomal peptide natural products","volume":"9","author":"Mohimani","year":"2014","journal-title":"ACS Chem. Biol"},{"key":"2023062712343805600_btz374-B33","doi-asserted-by":"crossref","first-page":"1902","DOI":"10.1021\/np500370c","article-title":"NRPquest: coupling mass spectrometry and genome mining for nonribosomal peptide discovery","volume":"77","author":"Mohimani","year":"2014","journal-title":"J. Nat. Prod"},{"key":"2023062712343805600_btz374-B34","doi-asserted-by":"crossref","first-page":"30.","DOI":"10.1038\/nchembio.2219","article-title":"Dereplication of peptidic natural products through database search of mass spectra","volume":"13","author":"Mohimani","year":"2017","journal-title":"Nat. Chem. Biol"},{"year":"2017","author":"Mohimani","key":"2023062712343805600_btz374-B35"},{"key":"2023062712343805600_btz374-B36","doi-asserted-by":"crossref","first-page":"596.","DOI":"10.1038\/nmeth.1350","article-title":"Dereplication and de novo sequencing of nonribosomal peptides","volume":"6","author":"Ng","year":"2009","journal-title":"Nat. Methods"},{"key":"2023062712343805600_btz374-B37","doi-asserted-by":"crossref","first-page":"16197","DOI":"10.1038\/nmicrobiol.2016.197","article-title":"Indexing the Pseudomonas specialized metabolome enabled the discovery of poaeamide B and the bananamides","volume":"2","author":"Nguyen","year":"2016","journal-title":"Nat. Microbiol"},{"key":"2023062712343805600_btz374-B38","doi-asserted-by":"crossref","first-page":"D501","DOI":"10.1093\/nar\/gki025","article-title":"NCBI reference sequence (RefSeq): a curated non-redundant sequence database of genomes, transcripts and proteins","volume":"33","author":"Pruitt","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"2023062712343805600_btz374-B39","doi-asserted-by":"crossref","first-page":"4626","DOI":"10.1021\/ac050102d","article-title":"Inspect: identification of posttranslationally modified peptides from tandem mass spectra","volume":"77","author":"Tanner","year":"2005","journal-title":"Anal. Chem"},{"key":"2023062712343805600_btz374-B40","doi-asserted-by":"crossref","first-page":"7946","DOI":"10.1021\/acs.analchem.6b00770","article-title":"Hydrogen rearrangement rules: computational MS\/MS fragmentation and structure elucidation using MS-FINDER software","volume":"88","author":"Tsugawa","year":"2016","journal-title":"Anal. Chem"},{"key":"2023062712343805600_btz374-B41","doi-asserted-by":"crossref","first-page":"828.","DOI":"10.1038\/nbt.3597","article-title":"Sharing and community curation of mass spectrometry data with Global Natural Products Social molecular networking","volume":"34","author":"Wang","year":"2016","journal-title":"Nat. Biotechnol"},{"volume-title":"Antimicrobial Resistance: Global Report on Surveillance","year":"2014","key":"2023062712343805600_btz374-B42"},{"key":"2023062712343805600_btz374-B43","doi-asserted-by":"crossref","first-page":"1259","DOI":"10.1016\/j.chembiol.2015.08.008","article-title":"Exploration of nonribosomal peptide families with an automated informatic search algorithm","volume":"22","author":"Yang","year":"2015","journal-title":"Chem. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/14\/i315\/50720924\/bioinformatics_35_14_i315.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/14\/i315\/50720924\/bioinformatics_35_14_i315.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T12:35:21Z","timestamp":1687869321000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/14\/i315\/5529154"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":43,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2019,7,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz374","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2019,7]]},"published":{"date-parts":[[2019,7]]}}}