{"id":"https://openalex.org/W2099078041","doi":"https://doi.org/10.1186/1471-2105-14-s2-s24","title":"Mass spectrometry-based protein identification by integrating de novo sequencing with database searching","display_name":"Mass spectrometry-based protein identification by integrating de novo sequencing with database searching","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2099078041","doi":"https://doi.org/10.1186/1471-2105-14-s2-s24","mag":"2099078041","pmid":"https://pubmed.ncbi.nlm.nih.gov/23369017"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-14-s2-s24","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-14-s2-s24","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-S2-S24","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-S2-S24","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016552410","display_name":"Penghao Wang","orcid":"https://orcid.org/0000-0002-3751-3921"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Penghao Wang","raw_affiliation_strings":["Prince of Wales Clinical School, University of New South Wales, Australia. penghao.wang@unsw.edu.au","Prince of Wales Clinical School, University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince of Wales Clinical School, University of New South Wales, Australia. penghao.wang@unsw.edu.au","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Prince of Wales Clinical School, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103839148","display_name":"Susan R. Wilson","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I2802631561","display_name":"Australian Mathematical Sciences Institute","ror":"https://ror.org/00yn60108","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802631561"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Susan R Wilson","raw_affiliation_strings":["Mathematical Sciences Institute, Australian National University, Australia","Prince of Wales Clinical School, University of New South Wales, Australia","Prince of Wales Clinical School, University of New South Wales, , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematical Sciences Institute, Australian National University, Australia","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I2802631561"]},{"raw_affiliation_string":"Prince of Wales Clinical School, University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"Prince of Wales Clinical School, University of New South Wales, , Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016552410"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.9301,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.71545337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"S2","first_page":"S24","last_page":"S24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9825999736785889,"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":0.9825999736785889,"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":0.013700000010430813,"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/T12388","display_name":"Identification and Quantification in Food","score":0.0005000000237487257,"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/identification","display_name":"Identification (biology)","score":0.6969542503356934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6656009554862976},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.5286296606063843},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.52281653881073},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5213823914527893},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5116472840309143},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4256369471549988},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3512071967124939},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22268807888031006},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1143890917301178},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09781253337860107}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6969542503356934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656009554862976},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.5286296606063843},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.52281653881073},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5213823914527893},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5116472840309143},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4256369471549988},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3512071967124939},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22268807888031006},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1143890917301178},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09781253337860107},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","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":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-14-s2-s24","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-14-s2-s24","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-S2-S24","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:23369017","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23369017","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:77d4f59f48fd4231849a5b53183de8d9","is_oa":true,"landing_page_url":"https://doaj.org/article/77d4f59f48fd4231849a5b53183de8d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 14, Iss Suppl 2, p S24 (2013)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2552327","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3549845","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-14-s2-s24","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-14-s2-s24","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-14-S2-S24","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3341091825","display_name":null,"funder_award_id":"525453","funder_id":"https://openalex.org/F4320334705","funder_display_name":"National Health and Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"},{"id":"https://openalex.org/F4320334705","display_name":"National Health and Medical Research Council","ror":"https://ror.org/011kf5r70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2099078041.pdf","grobid_xml":"https://content.openalex.org/works/W2099078041.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1659313070","https://openalex.org/W1968063944","https://openalex.org/W1973051173","https://openalex.org/W1980366102","https://openalex.org/W1981593008","https://openalex.org/W1986893074","https://openalex.org/W1987325064","https://openalex.org/W1995693931","https://openalex.org/W1996792890","https://openalex.org/W1997091955","https://openalex.org/W2001848433","https://openalex.org/W2018375934","https://openalex.org/W2026465178","https://openalex.org/W2030578978","https://openalex.org/W2035283832","https://openalex.org/W2038615001","https://openalex.org/W2047275456","https://openalex.org/W2064023506","https://openalex.org/W2075036506","https://openalex.org/W2082006641","https://openalex.org/W2088899342","https://openalex.org/W2106882534","https://openalex.org/W2116007721","https://openalex.org/W2118938750","https://openalex.org/W2118993019","https://openalex.org/W2130706354","https://openalex.org/W2143639525","https://openalex.org/W2217546073"],"related_works":["https://openalex.org/W2898732673","https://openalex.org/W2410053581","https://openalex.org/W2383658677","https://openalex.org/W2003932708","https://openalex.org/W3123203398","https://openalex.org/W2284877871","https://openalex.org/W2138102289","https://openalex.org/W2037896692","https://openalex.org/W2136066520","https://openalex.org/W2354598492"],"abstract_inverted_index":{"BACKGROUND:":[0],"Mass":[1],"spectrometry-based":[2],"protein":[3,152],"identification":[4,12,153,175],"is":[5,86,138],"a":[6,57,63,130,149],"very":[7,90],"challenging":[8],"task.":[9],"The":[10,32],"main":[11],"approaches":[13,22],"include":[14],"de":[15,48,83,126,158],"novo":[16,49,84,127,159],"sequencing":[17,85,128,160],"and":[18,51,88,112],"database":[19,58,143,164],"searching.":[20,144,165],"Both":[21],"have":[23,147],"shortcomings,":[24],"so":[25],"an":[26,101],"integrative":[27,33,76,98,151],"approach":[28,34,77],"has":[29,78],"been":[30],"developed.":[31],"firstly":[35],"infers":[36],"partial":[37],"peptide":[38,65],"sequences,":[39],"known":[40],"as":[41],"tags,":[42],"directly":[43],"from":[44],"tandem":[45],"spectra":[46],"through":[47],"sequencing,":[50],"then":[52],"puts":[53],"these":[54,122],"sequences":[55],"into":[56,163],"search":[59,107],"to":[60,104,106,133],"see":[61],"if":[62],"close":[64],"match":[66],"can":[67,156],"be":[68],"found.":[69],"However":[70],"the":[71,124,134],"current":[72],"implementation":[73],"of":[74],"this":[75],"several":[79],"limitations.":[80],"Firstly,":[81],"simplistic":[82],"applied":[87],"only":[89],"short":[91],"sequence":[92,110,116],"tags":[93],"are":[94],"used.":[95],"Secondly,":[96],"most":[97],"methods":[99,123],"apply":[100],"algorithm":[102],"similar":[103],"BLAST":[105],"for":[108],"exact":[109],"matches":[111],"do":[113],"not":[114],"accommodate":[115],"errors":[117],"well.":[118],"Thirdly,":[119],"by":[120],"applying":[121],"integrated":[125],"makes":[129],"limited":[131],"contribution":[132],"scoring":[135],"model":[136],"which":[137,155],"still":[139],"largely":[140],"based":[141],"on":[142,167],"RESULTS:":[145],"We":[146],"developed":[148],"new":[150],"method":[154,172],"integrate":[157],"more":[161],"efficiently":[162],"Evaluated":[166],"large":[168],"real":[169],"datasets,":[170],"our":[171],"outperforms":[173],"popular":[174],"methods.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}