{"id":"https://openalex.org/W2130227336","doi":"https://doi.org/10.1142/s0218213005002405","title":"VECTOR SPACE INDEXING FOR BIOSEQUENCE SIMILARITY SEARCHES","display_name":"VECTOR SPACE INDEXING FOR BIOSEQUENCE SIMILARITY SEARCHES","publication_year":2005,"publication_date":"2005-09-20","ids":{"openalex":"https://openalex.org/W2130227336","doi":"https://doi.org/10.1142/s0218213005002405","mag":"2130227336"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213005002405","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213005002405","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5102900844","display_name":"\u00d6zg\u00fcr \u00d6zt\u00fcrk","orcid":"https://orcid.org/0000-0003-2605-4587"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"OZGUR OZTURK","raw_affiliation_strings":["Department of Computer Science and Engineering,  The Ohio State University, Columbus, OH 43210, USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering,  The Ohio State University, Columbus, OH 43210, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210, USA#TAB#","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078571347","display_name":"Hakan Ferhatosmano\u011flu","orcid":"https://orcid.org/0000-0002-5181-4712"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HAKAN FERHATOSMANOGLU","raw_affiliation_strings":["Department of Computer Science and Engineering,  Department of Biomedical Informatics, The Ohio State University,  Columbus, OH 43210, USA","Department of Computer Science and Engineering, Department of Biomedical Informatics, The Ohio State University, Columbus, OH 43210, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering,  Department of Biomedical Informatics, The Ohio State University,  Columbus, OH 43210, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Department of Biomedical Informatics, The Ohio State University, Columbus, OH 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102900844"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14665201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":"05","first_page":"811","last_page":"826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9941999912261963,"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/T11106","display_name":"Data Management and Algorithms","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7993433475494385},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7938427925109863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7155721187591553},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5524328947067261},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5397710204124451},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.5290058255195618},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5233718156814575},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5061232447624207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4282929599285126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3943783938884735},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.324718713760376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2624015808105469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2409815788269043}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7993433475494385},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7938427925109863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155721187591553},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5524328947067261},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5397710204124451},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.5290058255195618},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5233718156814575},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5061232447624207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4282929599285126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3943783938884735},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.324718713760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2624015808105469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2409815788269043},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218213005002405","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213005002405","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.2291","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.2291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~hakan/publications/DNA-vectorspace.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W36558993","https://openalex.org/W174476237","https://openalex.org/W938539187","https://openalex.org/W1536229846","https://openalex.org/W1590304139","https://openalex.org/W1990061958","https://openalex.org/W2001496424","https://openalex.org/W2010142086","https://openalex.org/W2025376161","https://openalex.org/W2045821558","https://openalex.org/W2061959470","https://openalex.org/W2103014446","https://openalex.org/W2106642566","https://openalex.org/W2118269922","https://openalex.org/W2128061541","https://openalex.org/W2131227307","https://openalex.org/W2161856697","https://openalex.org/W2167833054","https://openalex.org/W2168459716","https://openalex.org/W2171146318","https://openalex.org/W4236611442","https://openalex.org/W4240861547"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W2368606575","https://openalex.org/W1949910768","https://openalex.org/W2132753198","https://openalex.org/W2369874856","https://openalex.org/W2182477562","https://openalex.org/W2792185758","https://openalex.org/W2166822184"],"abstract_inverted_index":{"We":[0,37,52,106],"present":[1,82],"a":[2],"multi-dimensional":[3],"indexing":[4],"approach":[5],"for":[6,59,73,77,98],"fast":[7],"sequence":[8],"similarity":[9],"search":[10],"in":[11,42],"DNA":[12],"and":[13,28,46,64,69,90,94,115,123],"protein":[14],"databases.":[15],"In":[16],"particular,":[17],"we":[18,81],"propose":[19],"effective":[20,109],"transformations":[21],"of":[22,49,120],"subsequences":[23],"into":[24],"numerical":[25],"vector":[26],"domains":[27],"build":[29],"efficient":[30],"index":[31,110],"structures":[32],"on":[33,113,118,131],"the":[34,43,104,129],"transformed":[35,44,121],"vectors.":[36],"then":[38,107],"define":[39],"distance":[40,124],"functions":[41,97],"domain":[45],"examine":[47],"properties":[48],"these":[50],"functions.":[51,125],"experimentally":[53],"compared":[54],"their":[55],"(a)":[56],"approximation":[57,71],"quality":[58,72],"k-Nearest":[60],"Neighbor":[61],"(k-NN)":[62],"queries":[63],"both":[65],"(b)":[66],"pruning":[67],"ability":[68],"(c)":[70],"\u03b5-range":[74],"queries.":[75],"Results":[76],"k-NN":[78],"queries,":[79],"which":[80],"here,":[83],"show":[84],"that":[85],"our":[86],"proposed":[87],"distances":[88],"FD2":[89],"WD2":[91],"(i.e.":[92],"Frequency":[93],"Wavelet":[95],"Distance":[96],"2-grams)":[99],"perform":[100],"significantly":[101],"better":[102],"than":[103],"others.":[105],"develop":[108],"structures,":[111],"based":[112],"R-trees":[114],"scalar":[116],"quantization,":[117],"top":[119],"vectors":[122],"Promising":[126],"results":[127],"from":[128],"experiments":[130],"real":[132],"biosequence":[133],"data":[134],"sets":[135],"are":[136],"presented.":[137]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}