{"id":"https://openalex.org/W2060989759","doi":"https://doi.org/10.1186/1471-2105-9-534","title":"Optimal neighborhood indexing for protein similarity search","display_name":"Optimal neighborhood indexing for protein similarity search","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2060989759","doi":"https://doi.org/10.1186/1471-2105-9-534","mag":"2060989759","pmid":"https://pubmed.ncbi.nlm.nih.gov/19087280"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-9-534","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-534","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-534","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/10.1186/1471-2105-9-534","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012897398","display_name":"Pierre Peterlongo","orcid":"https://orcid.org/0000-0003-0776-6407"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Pierre Peterlongo","raw_affiliation_strings":["Symbiose team-project, IRISA INRIA, Rennes, France. pierre.peterlongo@irisa.fr","Symbiose team-project, IRISA INRIA, Rennes, France"],"affiliations":[{"raw_affiliation_string":"Symbiose team-project, IRISA INRIA, Rennes, France. pierre.peterlongo@irisa.fr","institution_ids":["https://openalex.org/I2802519937"]},{"raw_affiliation_string":"Symbiose team-project, IRISA INRIA, Rennes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055679303","display_name":"Laurent No\u00e9","orcid":"https://orcid.org/0000-0002-1170-8376"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210160005","display_name":"Computer Science Laboratory of Lille","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210160005"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent No\u00e9","raw_affiliation_strings":["INRIA Lille Nord-Europe, Lille, France","LIFL, CNRS, Universit\u00e9 Lille 1, Lille, France"],"affiliations":[{"raw_affiliation_string":"INRIA Lille Nord-Europe, Lille, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LIFL, CNRS, Universit\u00e9 Lille 1, Lille, France","institution_ids":["https://openalex.org/I4210160005","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008215565","display_name":"Dominique Lavenier","orcid":"https://orcid.org/0000-0003-2557-680X"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I11559806","display_name":"\u00c9cole Normale Sup\u00e9rieure Paris-Saclay","ror":"https://ror.org/00hx6zz33","country_code":"FR","type":"education","lineage":["https://openalex.org/I11559806","https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Lavenier","raw_affiliation_strings":["IRISA \u2013 ENS, Cachan, France"],"affiliations":[{"raw_affiliation_string":"IRISA \u2013 ENS, Cachan, France","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I11559806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101637382","display_name":"Van Hoa Nguyen","orcid":"https://orcid.org/0000-0003-0582-2129"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Van Hoa Nguyen","raw_affiliation_strings":["Symbiose team-project, IRISA INRIA, Rennes, France"],"affiliations":[{"raw_affiliation_string":"Symbiose team-project, IRISA INRIA, Rennes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012626407","display_name":"Gr\u00e9gory Kucherov","orcid":"https://orcid.org/0000-0001-5899-5424"},"institutions":[{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210160005","display_name":"Computer Science Laboratory of Lille","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210160005"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gregory Kucherov","raw_affiliation_strings":["INRIA Lille Nord-Europe, Lille, France","LIFL, CNRS, Universit\u00e9 Lille 1, Lille, France"],"affiliations":[{"raw_affiliation_string":"INRIA Lille Nord-Europe, Lille, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LIFL, CNRS, Universit\u00e9 Lille 1, Lille, France","institution_ids":["https://openalex.org/I4210160005","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036539061","display_name":"Mathieu Giraud","orcid":"https://orcid.org/0000-0003-2741-8047"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre Inria de l'Universit\u00e9 de Lille","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210160005","display_name":"Computer Science Laboratory of Lille","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210160005"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Giraud","raw_affiliation_strings":["INRIA Lille Nord-Europe, Lille, France","LIFL, CNRS, Universit\u00e9 Lille 1, Lille, France"],"affiliations":[{"raw_affiliation_string":"INRIA Lille Nord-Europe, Lille, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LIFL, CNRS, Universit\u00e9 Lille 1, Lille, France","institution_ids":["https://openalex.org/I4210160005","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5012897398"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2802519937"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.2757,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60143408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"9","issue":"1","first_page":"534","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9945999979972839,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.6297478675842285},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6106509566307068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6104697585105896},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5557255744934082},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49776721000671387},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4937358796596527},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.48842373490333557},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4671318829059601},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4635993540287018},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4359784424304962},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3895041346549988},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3212478756904602},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30554109811782837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2242838442325592}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6297478675842285},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6106509566307068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6104697585105896},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5557255744934082},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49776721000671387},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4937358796596527},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.48842373490333557},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4671318829059601},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4635993540287018},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4359784424304962},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3895041346549988},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3212478756904602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30554109811782837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2242838442325592},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"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":"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":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":9,"locations":[{"id":"doi:10.1186/1471-2105-9-534","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-534","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-534","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:19087280","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19087280","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:CiteSeerX.psu:10.1.1.208.9411","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.208.9411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/34/05/10/PDF/journal2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.656.4523","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.656.4523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/inria-00340510/document/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.735.2018","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.735.2018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/inria-00340510/file/journal2.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00340510v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00340510","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 2008, 9 (534), &#x27E8;10.1186/1471-2105-9-534&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:eae597ee295544c79584bbf1da487c1a","is_oa":true,"landing_page_url":"https://doaj.org/article/eae597ee295544c79584bbf1da487c1a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 9, Iss 1, p 534 (2008)","raw_type":"article"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/28372","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/28372","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2640386","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2640386","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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:10.1186/1471-2105-9-534","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-534","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-534","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":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2060989759.pdf","grobid_xml":"https://content.openalex.org/works/W2060989759.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W1483191758","https://openalex.org/W1525642766","https://openalex.org/W1538909774","https://openalex.org/W1555915743","https://openalex.org/W1815392837","https://openalex.org/W1955121107","https://openalex.org/W1975670646","https://openalex.org/W1982496832","https://openalex.org/W2006290495","https://openalex.org/W2015292449","https://openalex.org/W2029195137","https://openalex.org/W2055043387","https://openalex.org/W2062202510","https://openalex.org/W2066593167","https://openalex.org/W2087064593","https://openalex.org/W2094519647","https://openalex.org/W2097892623","https://openalex.org/W2099741047","https://openalex.org/W2129497695","https://openalex.org/W2131989567","https://openalex.org/W2136145671","https://openalex.org/W2143210482","https://openalex.org/W2157516796","https://openalex.org/W2158714788","https://openalex.org/W6631298684"],"related_works":["https://openalex.org/W3177062893","https://openalex.org/W3125143773","https://openalex.org/W803550684","https://openalex.org/W2007032764","https://openalex.org/W2483226803","https://openalex.org/W3143937874","https://openalex.org/W2067280619","https://openalex.org/W4251343851","https://openalex.org/W2149442301","https://openalex.org/W2143239491"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"practical":[3],"index":[4,26],"size":[5],"reduction":[6],"of":[7,18],"the":[8,16],"neighborhood":[9],"data,":[10],"that":[11],"does":[12],"not":[13],"negatively":[14],"affect":[15],"performance":[17],"large-scale":[19],"search":[20],"in":[21,30,50],"protein":[22,35],"sequences.":[23],"Such":[24],"an":[25,54],"can":[27,47],"be":[28],"used":[29],"any":[31,51],"study":[32,52],"involving":[33,53],"large":[34],"data.":[36],"Moreover,":[37],"rectangular":[38],"substitution":[39],"score":[40],"matrices":[41],"and":[42],"their":[43],"associated":[44],"statistical":[45],"parameters":[46],"have":[48],"applications":[49],"alphabet":[55],"reduction.":[56]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
