{"id":"https://openalex.org/W1987325064","doi":"https://doi.org/10.1089/106652703763255633","title":"A Suboptimal Algorithm for <i>De Novo</i> Peptide Sequencing via Tandem Mass Spectrometry","display_name":"A Suboptimal Algorithm for <i>De Novo</i> Peptide Sequencing via Tandem Mass Spectrometry","publication_year":2003,"publication_date":"2003-02-01","ids":{"openalex":"https://openalex.org/W1987325064","doi":"https://doi.org/10.1089/106652703763255633","mag":"1987325064","pmid":"https://pubmed.ncbi.nlm.nih.gov/12676047"},"language":"en","primary_location":{"id":"doi:10.1089/106652703763255633","is_oa":false,"landing_page_url":"https://doi.org/10.1089/106652703763255633","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040553846","display_name":"Bingwen Lu","orcid":"https://orcid.org/0000-0001-5877-6459"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingwen Lu","raw_affiliation_strings":["Molecular and Computational Biology Program, Department of Biological Sciences, University of Southern California, Los Angeles, CA 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular and Computational Biology Program, Department of Biological Sciences, University of Southern California, Los Angeles, CA 90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443173","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-8414-6346"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["Molecular and Computational Biology Program, Department of Biological Sciences, University of Southern California, Los Angeles, CA 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Molecular and Computational Biology Program, Department of Biological Sciences, University of Southern California, Los Angeles, CA 90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":5.026,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.96346454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tandem-mass-spectrometry","display_name":"Tandem mass spectrometry","score":0.8294306993484497},{"id":"https://openalex.org/keywords/mass-spectrometry","display_name":"Mass spectrometry","score":0.6377689838409424},{"id":"https://openalex.org/keywords/peptide","display_name":"Peptide","score":0.6328088045120239},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.6290098428726196},{"id":"https://openalex.org/keywords/tandem-mass-tag","display_name":"Tandem mass tag","score":0.5970458984375},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.5256734490394592},{"id":"https://openalex.org/keywords/ion","display_name":"Ion","score":0.4185160994529724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3479965925216675},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.20749041438102722},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1689552366733551},{"id":"https://openalex.org/keywords/quantitative-proteomics","display_name":"Quantitative proteomics","score":0.13449978828430176},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.11210843920707703},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09937798976898193},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07607468962669373}],"concepts":[{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.8294306993484497},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.6377689838409424},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.6328088045120239},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.6290098428726196},{"id":"https://openalex.org/C86153913","wikidata":"https://www.wikidata.org/wiki/Q7682439","display_name":"Tandem mass tag","level":5,"score":0.5970458984375},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.5256734490394592},{"id":"https://openalex.org/C145148216","wikidata":"https://www.wikidata.org/wiki/Q36496","display_name":"Ion","level":2,"score":0.4185160994529724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3479965925216675},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.20749041438102722},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1689552366733551},{"id":"https://openalex.org/C80311884","wikidata":"https://www.wikidata.org/wiki/Q7268939","display_name":"Quantitative proteomics","level":4,"score":0.13449978828430176},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.11210843920707703},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09937798976898193},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07607468962669373},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001798","descriptor_name":"Blood Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001798","descriptor_name":"Blood Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001798","descriptor_name":"Blood Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002417","descriptor_name":"Cattle","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002417","descriptor_name":"Cattle","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002417","descriptor_name":"Cattle","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012710","descriptor_name":"Serum Albumin, Bovine","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012710","descriptor_name":"Serum Albumin, Bovine","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012710","descriptor_name":"Serum Albumin, Bovine","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1089/106652703763255633","is_oa":false,"landing_page_url":"https://doi.org/10.1089/106652703763255633","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:12676047","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12676047","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5495813962","display_name":null,"funder_award_id":"1-R01-RR16522-01","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1964443249","https://openalex.org/W1974909424","https://openalex.org/W1981337935","https://openalex.org/W1981593008","https://openalex.org/W1995693931","https://openalex.org/W2001848433","https://openalex.org/W2026465178","https://openalex.org/W2085484405","https://openalex.org/W2102412629","https://openalex.org/W2103619713","https://openalex.org/W2106773613","https://openalex.org/W2145361425","https://openalex.org/W2150746288","https://openalex.org/W2752885492","https://openalex.org/W3136323740"],"related_works":["https://openalex.org/W2586138576","https://openalex.org/W2334381244","https://openalex.org/W4224255595","https://openalex.org/W2032237072","https://openalex.org/W2416605037","https://openalex.org/W2042338933","https://openalex.org/W2087305601","https://openalex.org/W2942299869","https://openalex.org/W2414697561","https://openalex.org/W2081759908"],"abstract_inverted_index":{"Tandem":[0,17],"mass":[1,18,56],"spectrometry":[2,19],"has":[3,117],"emerged":[4],"to":[5,48],"be":[6],"one":[7],"of":[8,24,38,59,113],"the":[9,35,50,70,92,101,111],"most":[10],"powerful":[11],"high-throughput":[12],"techniques":[13],"for":[14],"protein":[15,66],"identification.":[16],"selects":[20],"and":[21,29,32,86,120],"fragments":[22],"peptides":[23],"interest":[25],"into":[26,73],"N-terminal":[27],"ions":[28],"C-terminal":[30],"ions,":[31],"it":[33],"measures":[34],"mass/charge":[36],"ratios":[37],"these":[39],"ions.":[40],"The":[41,115,125],"de":[42],"novo":[43],"peptide":[44,51],"sequencing":[45],"problem":[46],"is":[47,110,127],"derive":[49],"sequences":[52],"from":[53],"given":[54],"tandem":[55],"spectral":[57,71],"data":[58,72],"k":[60],"ion":[61],"peaks":[62],"without":[63],"searching":[64],"against":[65],"databases.":[67],"By":[68],"transforming":[69],"a":[74],"matrix":[75],"spectrum":[76],"graph":[77],"G":[78],"=":[79,84,88],"(V,":[80],"E),":[81],"where":[82,108],"|V|":[83],"O(k(2))":[85],"|E|":[87],"O(k(3)),":[89],"we":[90],"give":[91],"first":[93],"polynomial":[94],"time":[95],"suboptimal":[96,102],"algorithm":[97,116],"that":[98],"finds":[99],"all":[100],"solutions":[103],"(peptides)":[104],"in":[105],"O(p|E|)":[106],"time,":[107],"p":[109],"number":[112],"solutions.":[114],"been":[118],"implemented":[119],"tested":[121],"on":[122],"experimental":[123],"data.":[124],"program":[126],"available":[128],"at":[129],"http://hto-c.usc.edu:8000/msms/menu/denovo.htm.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2016-06-24T00:00:00"}