{"id":"https://openalex.org/W2017064873","doi":"https://doi.org/10.1142/9789812701626_0021","title":"A MACHINE LEARNING APPROACH TO PREDICTING PEPTIDE FRAGMENTATION SPECTRA","display_name":"A MACHINE LEARNING APPROACH TO PREDICTING PEPTIDE FRAGMENTATION SPECTRA","publication_year":2005,"publication_date":"2005-12-01","ids":{"openalex":"https://openalex.org/W2017064873","doi":"https://doi.org/10.1142/9789812701626_0021","mag":"2017064873","pmid":"https://pubmed.ncbi.nlm.nih.gov/17094241"},"language":"en","primary_location":{"id":"doi:10.1142/9789812701626_0021","doi":"https://doi.org/10.1142/9789812701626_0021","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812701626_0021","pdf_url":null,"source":{"id":"https://openalex.org/S7407088813","display_name":"Pacific Symposium on Biocomputing (PSB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biocomputing 2006","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5084242084","display_name":"Randy J. Arnold","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"RANDY J. ARNOLD","raw_affiliation_strings":["Department of Chemistry, Indiana University, Bloomington, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Indiana University, Bloomington, IN 47405, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715143","display_name":"NARMADA JAYASANKAR","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"NARMADA JAYASANKAR","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, IN 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016514083","display_name":"Divya Aggarwal","orcid":"https://orcid.org/0000-0001-9031-9549","observed_orcids":["https://orcid.org/0000-0001-9031-9549","https://orcid.org/0009-0000-5479-9098"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DIVYA AGGARWAL","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, IN 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078007096","display_name":"Haixu Tang","orcid":"https://orcid.org/0000-0001-8963-8155","observed_orcids":["https://orcid.org/0000-0001-8963-8155"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HAIXU TANG","raw_affiliation_strings":["Center for Genomics and Bioinformatics. Indiana University, Bloomington, IN 47405, USA","School of Informatics, Indiana University, Bloomington, IN 47408, USA","School of Informatics, Indiana University, Bloomington, IN 47408, USACenter for Genomics and Bioinformatics. Indiana University, Bloomington, IN 47405, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Genomics and Bioinformatics. Indiana University, Bloomington, IN 47405, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, IN 47408, USACenter for Genomics and Bioinformatics. Indiana University, Bloomington, IN 47405, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051324698","display_name":"Predrag Radivojac A","orcid":"https://orcid.org/0000-0002-6769-0793","observed_orcids":["https://orcid.org/0000-0002-6769-0793","https://orcid.org/0000-0001-8713-9213"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"PREDRAG RADIVOJAC","raw_affiliation_strings":["School of Informatics, Indiana University, Bloomington, IN 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Indiana University, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.1183,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97967086,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.8690999746322632,"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":0.8690999746322632,"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":0.11900000274181366,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0020000000949949026,"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":0.9430000185966492},{"id":"https://openalex.org/keywords/peptide-identification","display_name":"peptide identification","score":0.9290000200271606},{"id":"https://openalex.org/keywords/de-novo-sequencing","display_name":"de novo sequencing","score":0.699999988079071},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.8379999995231628},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"posterior probability","score":0.8100000023841858},{"id":"https://openalex.org/keywords/fragmentation-rules","display_name":"fragmentation rules","score":0.7480000257492065},{"id":"https://openalex.org/keywords/database-searching","display_name":"database searching","score":0.531000018119812},{"id":"https://openalex.org/keywords/proteomics","display_name":"proteomics","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.7654559016227722},{"id":"https://openalex.org/C31827203","wikidata":"https://www.wikidata.org/wiki/Q874296","display_name":"Tandem mass spectrometry","level":3,"score":0.6154910326004028},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.6141323447227478},{"id":"https://openalex.org/C162356407","wikidata":"https://www.wikidata.org/wiki/Q180809","display_name":"Mass spectrometry","level":2,"score":0.5721009373664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5290837287902832},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.5129342079162598},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49392205476760864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4213167428970337},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.37192851305007935},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.21381226181983948},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.15808382630348206},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.08097192645072937},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.06673339009284973},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1142/9789812701626_0021","doi":"https://doi.org/10.1142/9789812701626_0021","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812701626_0021","pdf_url":null,"source":{"id":"https://openalex.org/S7407088813","display_name":"Pacific Symposium on Biocomputing (PSB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biocomputing 2006","raw_type":"proceedings-article"},{"id":"pmid:17094241","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17094241","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":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","raw_type":"Evaluation Study"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2125055259"],"related_works":["https://openalex.org/W7096615613","https://openalex.org/W3194179035","https://openalex.org/W7097651389","https://openalex.org/W2325069297","https://openalex.org/W2119190889","https://openalex.org/W2029042807","https://openalex.org/W2001643892","https://openalex.org/W2330629086","https://openalex.org/W2095767296","https://openalex.org/W2945525532"],"abstract_inverted_index":{"Accurate":[0],"peptide":[1,36,68,89,96,110,147],"identification":[2,37],"from":[3],"tandem":[4],"mass":[5,76,114],"spectrometry":[6],"experiments":[7],"is":[8,46,80,143],"the":[9,31,51,58,64,117,136,152],"cornerstone":[10],"of":[11,35,57,67,119,126,138,156],"proteomics.":[12],"Although":[13],"various":[14,123],"approaches":[15,84],"for":[16,122,145],"matching":[17],"database":[18,148],"sequences":[19],"with":[20,61],"experimental":[21],"spectra":[22,91],"have":[23,38],"been":[24],"developed":[25],"to":[26,50,63,85,108],"date":[27],"(e.g.":[28],"Sequest,":[29],"Mascot)":[30],"sensitivity":[32],"and":[33,55,70,128,150,162],"specificity":[34],"not":[39],"yet":[40],"reached":[41],"their":[42],"full":[43],"potential.":[44],"This":[45],"in":[47,113,116],"part":[48],"due":[49],"tradeoffs":[52],"between":[53],"robustness":[54],"accuracy":[56,137],"existing":[59],"methods":[60],"respect":[62],"non-uniform":[65],"nature":[66],"fragmentation":[69,90,111,157],"bond":[71],"cleavages":[72],"induced":[73],"by":[74],"different":[75],"spectrometers.":[77],"Accordingly,":[78],"it":[79],"expected":[81],"that":[82,135,151],"new":[83],"de":[86],"novo":[87],"predicting":[88],"will":[92],"enable":[93],"more":[94],"accurate":[95],"identification.":[97],"To":[98],"address":[99],"this":[100],"problem,":[101],"here":[102],"we":[103],"used":[104],"a":[105],"data-driven":[106],"approach":[107],"learn":[109],"rules":[112,155],"spectrometry,":[115],"form":[118],"posterior":[120],"probabilities,":[121],"fragment-ion":[124],"types":[125],"doubly":[127],"triply":[129],"charged":[130],"precursor":[131,163],"ions.":[132],"We":[133],"show":[134],"our":[139],"neural-network":[140],"based":[141],"methodology":[142],"useful":[144,154],"subsequent":[146],"searches":[149],"most":[153],"significantly":[158],"differ":[159],"across":[160],"ion":[161],"types.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}