{"id":"https://openalex.org/W2162089072","doi":"https://doi.org/10.1186/1471-2105-13-324","title":"Hydra: a scalable proteomic search engine which utilizes the Hadoop distributed computing framework","display_name":"Hydra: a scalable proteomic search engine which utilizes the Hadoop distributed computing framework","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2162089072","doi":"https://doi.org/10.1186/1471-2105-13-324","mag":"2162089072","pmid":"https://pubmed.ncbi.nlm.nih.gov/23216909"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-324","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-324","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-324","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/10.1186/1471-2105-13-324","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073785908","display_name":"Steven M. Lewis","orcid":"https://orcid.org/0000-0002-1979-0554"},"institutions":[{"id":"https://openalex.org/I3148997608","display_name":"Institute for Systems Biology","ror":"https://ror.org/02tpgw303","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3148997608"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven Lewis","raw_affiliation_strings":["Institute for Systems Biology, Seattle, WA, USA. steven.lewis@systemsbiology.org","Institute for Systems Biology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Systems Biology, Seattle, WA, USA. steven.lewis@systemsbiology.org","institution_ids":["https://openalex.org/I3148997608"]},{"raw_affiliation_string":"Institute for Systems Biology, Seattle, WA, USA","institution_ids":["https://openalex.org/I3148997608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090269921","display_name":"Attila Csord\u00e1s","orcid":"https://orcid.org/0000-0003-3576-1793"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Attila Csordas","raw_affiliation_strings":["PRIDE Group Proteomics Services Team EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PRIDE Group Proteomics Services Team EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005430904","display_name":"Sarah Killcoyne","orcid":"https://orcid.org/0000-0003-3686-6167"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Sarah Killcoyne","raw_affiliation_strings":["Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Luxembourg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Luxembourg, Germany","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066783652","display_name":"Henning Hermjakob","orcid":"https://orcid.org/0000-0001-8479-0262"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Henning Hermjakob","raw_affiliation_strings":["PRIDE Group Proteomics Services Team EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PRIDE Group Proteomics Services Team EMBL European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018903678","display_name":"Michael R. Hoopmann","orcid":"https://orcid.org/0000-0001-7029-7792"},"institutions":[{"id":"https://openalex.org/I3148997608","display_name":"Institute for Systems Biology","ror":"https://ror.org/02tpgw303","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3148997608"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael R Hoopmann","raw_affiliation_strings":["Institute for Systems Biology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Systems Biology, Seattle, WA, USA","institution_ids":["https://openalex.org/I3148997608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036737482","display_name":"Robert L. Moritz","orcid":"https://orcid.org/0000-0002-3216-9447"},"institutions":[{"id":"https://openalex.org/I3148997608","display_name":"Institute for Systems Biology","ror":"https://ror.org/02tpgw303","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3148997608"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert L Moritz","raw_affiliation_strings":["Institute for Systems Biology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Systems Biology, Seattle, WA, USA","institution_ids":["https://openalex.org/I3148997608"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070102563","display_name":"Eric W. Deutsch","orcid":"https://orcid.org/0000-0001-8732-0928"},"institutions":[{"id":"https://openalex.org/I3148997608","display_name":"Institute for Systems Biology","ror":"https://ror.org/02tpgw303","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3148997608"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric W Deutsch","raw_affiliation_strings":["Institute for Systems Biology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Systems Biology, Seattle, WA, USA","institution_ids":["https://openalex.org/I3148997608"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056677361","display_name":"John Boyle","orcid":"https://orcid.org/0000-0002-5378-5361"},"institutions":[{"id":"https://openalex.org/I3148997608","display_name":"Institute for Systems Biology","ror":"https://ror.org/02tpgw303","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3148997608"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Boyle","raw_affiliation_strings":["Institute for Systems Biology, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Systems Biology, Seattle, WA, USA","institution_ids":["https://openalex.org/I3148997608"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073785908"],"corresponding_institution_ids":["https://openalex.org/I3148997608"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":2.7437,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.9032528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"324","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9825000166893005,"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":0.9825000166893005,"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":0.002300000051036477,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.0017000000225380063,"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/scalability","display_name":"Scalability","score":0.8371909856796265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8271118998527527},{"id":"https://openalex.org/keywords/shotgun-proteomics","display_name":"Shotgun proteomics","score":0.5473794937133789},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.54624342918396},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.513043999671936},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4872967004776001},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4569151997566223},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4397760033607483},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4351046085357666},{"id":"https://openalex.org/keywords/database-search-engine","display_name":"Database search engine","score":0.4205617308616638},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4001929759979248},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39513352513313293},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3814772069454193},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.291511595249176},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19307902455329895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.13235434889793396}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8371909856796265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271118998527527},{"id":"https://openalex.org/C68289359","wikidata":"https://www.wikidata.org/wiki/Q7502514","display_name":"Shotgun proteomics","level":4,"score":0.5473794937133789},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.54624342918396},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.513043999671936},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4872967004776001},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4569151997566223},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4397760033607483},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4351046085357666},{"id":"https://openalex.org/C48000682","wikidata":"https://www.wikidata.org/wiki/Q5227411","display_name":"Database search engine","level":3,"score":0.4205617308616638},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4001929759979248},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39513352513313293},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3814772069454193},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.291511595249176},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19307902455329895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.13235434889793396},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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":"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":"D011499","descriptor_name":"Protein Processing, Post-Translational","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011499","descriptor_name":"Protein Processing, Post-Translational","qualifier_ui":null,"qualifier_name":null,"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":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","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},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-13-324","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-324","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-324","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:23216909","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23216909","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:c337c57d111842dba015536a46ba3934","is_oa":false,"landing_page_url":"https://doaj.org/article/c337c57d111842dba015536a46ba3934","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 13, Iss 1, p 324 (2012)","raw_type":"article"},{"id":"pmh:oai:orbilu.uni.lu:10993/642","is_oa":true,"landing_page_url":"http://orbilu.uni.lu/handle/10993/642","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 13, 324 (2012)","raw_type":"peer reviewed"},{"id":"pmh:oai:pubmedcentral.nih.gov:3538679","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3538679","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-13-324","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-324","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-324","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G1379372628","display_name":null,"funder_award_id":"2P50 GM076547/Center for Systems Biology","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G5638855441","display_name":null,"funder_award_id":"2P50 GM076547","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7098221883","display_name":null,"funder_award_id":"2P50 GM076547","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7724812965","display_name":null,"funder_award_id":"R01GM087221","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8352735058","display_name":null,"funder_award_id":"R01GM087221","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G8511132011","display_name":null,"funder_award_id":"GM076547","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G945240375","display_name":null,"funder_award_id":"2P50 GM076547/Center for Systems Biology","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320310700","display_name":"Universit\u00e9 du Luxembourg","ror":"https://ror.org/036x5ad56"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2162089072.pdf","grobid_xml":"https://content.openalex.org/works/W2162089072.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W1968044788","https://openalex.org/W2003137843","https://openalex.org/W2011354186","https://openalex.org/W2026465178","https://openalex.org/W2047275456","https://openalex.org/W2058135122","https://openalex.org/W2068016108","https://openalex.org/W2091754843","https://openalex.org/W2112078820","https://openalex.org/W2116063068","https://openalex.org/W2121762798","https://openalex.org/W2125947965","https://openalex.org/W2130706354","https://openalex.org/W2131806062","https://openalex.org/W2132899146","https://openalex.org/W2153653863","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W4282568653","https://openalex.org/W2082868123","https://openalex.org/W2182041029","https://openalex.org/W2064605021","https://openalex.org/W2793208063","https://openalex.org/W2161598609","https://openalex.org/W3112159008","https://openalex.org/W2282020652","https://openalex.org/W2119380317","https://openalex.org/W2070155952"],"abstract_inverted_index":{"BACKGROUND:":[0],"For":[1],"shotgun":[2],"mass":[3,32],"spectrometry":[4],"based":[5],"proteomics":[6],"the":[7,15,43,81,91,98,103,109,114,118,150,155,162],"most":[8],"computationally":[9],"expensive":[10],"step":[11],"is":[12,47,50,74,111,124,129],"in":[13,131,154],"matching":[14],"spectra":[16],"against":[17],"an":[18,38],"increasingly":[19],"large":[20,137,143],"database":[21,70],"of":[22,45,108,120,145,152],"sequences":[23],"and":[24,42,113,142],"their":[25],"post-translational":[26],"modifications":[27,141],"with":[28,149,161],"known":[29],"masses.":[30],"Each":[31],"spectrometer":[33],"can":[34],"generate":[35],"data":[36],"at":[37],"astonishingly":[39],"high":[40],"rate,":[41],"scope":[44],"what":[46],"searched":[48],"for":[49,55,97,117],"continually":[51],"increasing.":[52],"Therefore":[53],"solutions":[54],"improving":[56],"our":[57],"ability":[58,133],"to":[59,77,134,159],"perform":[60],"these":[61],"searches":[62],"are":[63],"needed.":[64],"RESULTS:":[65],"We":[66],"present":[67],"a":[68,136],"sequence":[69],"search":[71,88],"engine":[72,89],"that":[73],"specifically":[75],"designed":[76],"run":[78],"efficiently":[79],"on":[80],"Hadoop":[82],"MapReduce":[83],"distributed":[84,122],"computing":[85],"framework.":[86],"The":[87,106,127],"implements":[90],"K-score":[92],"algorithm,":[93],"generating":[94],"comparable":[95],"output":[96],"same":[99],"input":[100],"files":[101],"as":[102],"original":[104],"implementation.":[105],"scalability":[107],"system":[110],"shown,":[112],"architecture":[115],"required":[116],"development":[119],"such":[121],"processing":[123],"discussed.":[125],"CONCLUSION:":[126],"software":[128],"scalable":[130],"its":[132],"handle":[135],"peptide":[138],"database,":[139],"numerous":[140],"numbers":[144],"spectra.":[146],"Performance":[147],"scales":[148],"number":[151],"processors":[153],"cluster,":[156],"allowing":[157],"throughput":[158],"expand":[160],"available":[163],"resources.":[164]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}