{"id":"https://openalex.org/W2045985536","doi":"https://doi.org/10.1021/pr050011x","title":"Peptide Sequence Tags for Fast Database Search in Mass-Spectrometry","display_name":"Peptide Sequence Tags for Fast Database Search in Mass-Spectrometry","publication_year":2005,"publication_date":"2005-06-15","ids":{"openalex":"https://openalex.org/W2045985536","doi":"https://doi.org/10.1021/pr050011x","mag":"2045985536","pmid":"https://pubmed.ncbi.nlm.nih.gov/16083278"},"language":"en","primary_location":{"id":"doi:10.1021/pr050011x","doi":"https://doi.org/10.1021/pr050011x","is_oa":false,"landing_page_url":"https://doi.org/10.1021/pr050011x","pdf_url":null,"source":{"id":"https://openalex.org/S74367812","display_name":"Journal of Proteome Research","issn_l":"1535-3893","issn":["1535-3893","1535-3907"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-d","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Proteome Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5008016937","display_name":"Ari M. Frank","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ari Frank","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008832336","display_name":"Stephen W. Tanner","orcid":"https://orcid.org/0000-0002-4816-5547","observed_orcids":["https://orcid.org/0000-0002-4816-5547"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Tanner","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028801735","display_name":"Vineet Bafna","orcid":"https://orcid.org/0000-0002-5810-6241","observed_orcids":["https://orcid.org/0000-0002-5810-6241"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vineet Bafna","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027480961","display_name":"Pavel A. Pevzner","orcid":"https://orcid.org/0000-0002-0418-165X","observed_orcids":["https://orcid.org/0000-0002-0418-165X"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel Pevzner","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0114 and Bioinformatics Program, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0419","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":4500,"currency":"USD","value_usd":4500},"apc_paid":null,"fwci":6.5522,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.97869593,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"4","issue":"4","first_page":"1287","last_page":"1295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.986299991607666,"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":0.986299991607666,"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":0.009999999776482582,"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":0.0006000000284984708,"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/peptide-identification","display_name":"peptide identification","score":0.5590000152587891},{"id":"https://openalex.org/keywords/probability-models","display_name":"probability models","score":0.5410000085830688},{"id":"https://openalex.org/keywords/post-translational-modification","display_name":"post-translational modification","score":0.8259999752044678},{"id":"https://openalex.org/keywords/de-novo-sequencing","display_name":"de novo sequencing","score":0.8479999899864197},{"id":"https://openalex.org/keywords/search-speed","display_name":"search speed","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.6695517897605896},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.5720593929290771},{"id":"https://openalex.org/C184185385","wikidata":"https://www.wikidata.org/wiki/Q6085263","display_name":"Isobaric labeling","level":5,"score":0.5521214008331299},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5145813822746277},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4769769608974457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43038511276245117},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.4161342978477478},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.4153411090373993},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40467149019241333},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3991296589374542},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37372738122940063},{"id":"https://openalex.org/C202157981","wikidata":"https://www.wikidata.org/wiki/Q7251488","display_name":"Protein mass spectrometry","level":4,"score":0.3583526015281677},{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.330961138010025},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.3098306953907013},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15929347276687622},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.12291890382766724},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013058","descriptor_name":"Mass Spectrometry","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D013223","descriptor_name":"Statistics as Topic","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":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/pr050011x","doi":"https://doi.org/10.1021/pr050011x","is_oa":false,"landing_page_url":"https://doi.org/10.1021/pr050011x","pdf_url":null,"source":{"id":"https://openalex.org/S74367812","display_name":"Journal of Proteome Research","issn_l":"1535-3893","issn":["1535-3893","1535-3907"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-d","doyens","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Proteome Research","raw_type":"journal-article"},{"id":"pmid:16083278","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16083278","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,"listed_in":[],"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 proteome research","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5695265255","display_name":"Algorithms & Software for Computational Mass Spectrometry","funder_award_id":"R01RR016522","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"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":23,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1543113652","https://openalex.org/W1968868346","https://openalex.org/W1974791474","https://openalex.org/W1980366102","https://openalex.org/W1981593008","https://openalex.org/W1987445292","https://openalex.org/W1988667155","https://openalex.org/W1995693931","https://openalex.org/W1996600592","https://openalex.org/W2001848433","https://openalex.org/W2015556811","https://openalex.org/W2016701426","https://openalex.org/W2034645824","https://openalex.org/W2038615001","https://openalex.org/W2058135122","https://openalex.org/W2072000480","https://openalex.org/W2079056345","https://openalex.org/W2085393537","https://openalex.org/W2095898845","https://openalex.org/W2112078820","https://openalex.org/W2131362052","https://openalex.org/W2150746288"],"related_works":["https://openalex.org/W7100712447","https://openalex.org/W2577463509","https://openalex.org/W6979820308","https://openalex.org/W2075036506","https://openalex.org/W1504698380","https://openalex.org/W7096460611","https://openalex.org/W2375482231","https://openalex.org/W2076516903","https://openalex.org/W2004515150","https://openalex.org/W2146980169"],"abstract_inverted_index":{"Filtration":[0],"techniques":[1],"in":[2,22,47,86,121],"the":[3,13,34,37,87,102,113,119,123,138,170],"form":[4],"of":[5,8,19,41,73,104,126,140],"rapid":[6],"elimination":[7],"candidate":[9],"sequences":[10],"while":[11],"retaining":[12],"true":[14],"one":[15],"are":[16,57],"key":[17,38],"ingredients":[18],"database":[20,108],"searches":[21,109],"genomics.":[23],"Although":[24],"SEQUEST":[25],"and":[26,116],"Mascot":[27],"perform":[28],"a":[29,51,133,149],"conceptually":[30],"similar":[31],"task":[32],"to":[33,147],"tool":[35],"BLAST,":[36],"algorithmic":[39],"idea":[40],"BLAST":[42,97],"(filtration)":[43],"was":[44],"never":[45],"implemented":[46],"these":[48,82],"tools.":[49],"As":[50],"result":[52],"MS/MS":[53,107],"protein":[54,127],"identification":[55],"tools":[56,83],"becoming":[58],"too":[59,84,98],"time-consuming":[60],"for":[61,66,106,136],"many":[62],"applications":[63],"including":[64],"search":[65],"post-translationally":[67],"modified":[68],"peptides.":[69],"Moreover,":[70],"matching":[71],"millions":[72],"spectra":[74],"against":[75],"all":[76],"known":[77],"proteins":[78],"will":[79],"soon":[80],"make":[81],"slow":[85],"same":[88],"way":[89],"that":[90,110],"\"genome":[91],"vs":[92],"genome\"":[93],"comparisons":[94],"instantly":[95],"made":[96],"slow.":[99],"We":[100],"describe":[101],"development":[103],"filters":[105],"dramatically":[111],"reduce":[112],"running":[114],"time":[115],"effectively":[117],"remove":[118],"bottlenecks":[120],"searching":[122],"huge":[124],"space":[125],"modifications.":[128],"Our":[129,154],"approach,":[130],"based":[131],"on":[132],"probability":[134],"model":[135],"determining":[137],"accuracy":[139],"sequence":[141],"tags,":[142],"achieves":[143],"superior":[144],"results":[145],"compared":[146],"GutenTag,":[148],"popular":[150],"tag":[151,155],"generation":[152],"algorithm.":[153],"generating":[156],"algorithm":[157,164],"along":[158],"with":[159],"our":[160],"de":[161],"novo":[162],"sequencing":[163],"PepNovo":[165],"can":[166],"be":[167],"accessed":[168],"via":[169],"URL":[171],"http://peptide.ucsd.edu/.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
